© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 8-LLAMASCOPE-RES-32K
    11. 17930
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to preparedness and contingency planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    prepared

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ture
    -0.16
    ÑĥзÑĭ
    -0.16
    AspNet
    -0.15
    Äįet
    -0.15
    hem
    -0.15
    ubar
    -0.14
    RTOS
    -0.14
    Âłmi
    -0.14
    .scalar
    -0.14
    éĴŁ
    -0.14
    POSITIVE LOGITS
    563
    0.17
    stro
    0.17
     prepared
    0.15
    543
    0.15
    824
    0.15
    _cre
    0.15
     cre
    0.15
    .Lib
    0.14
    FA
    0.14
     sweep
    0.14
    Activations Density 0.103%

    No Known Activations