© 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. 6-LLAMASCOPE-RES-32K
    11. 31813
    Prev
    Next
    INDEX
    Explanations

    terms related to pest control services and their professional attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rex
    -0.17
    ýt
    -0.15
    ystate
    -0.15
    lant
    -0.15
    abwe
    -0.15
     Ik
    -0.15
    chrift
    -0.15
    isol
    -0.14
    ÙĪاÙĩ
    -0.14
    ostel
    -0.14
    POSITIVE LOGITS
    оже
    0.14
    ald
    0.14
    ener
    0.14
    _SAFE
    0.14
    ape
    0.14
    ½Ķ
    0.13
    arts
    0.13
    iders
    0.13
    ots
    0.13
    okol
    0.13
    Activations Density 0.021%

    No Known Activations