© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 23-LLAMASCOPE-RES-32K
    11. 1862
    Prev
    Next
    INDEX
    Explanations

    common verbs and pronouns that signal presence and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     remaining
    -0.17
     someone
    -0.14
     bottom
    -0.14
    (original
    -0.14
     initial
    -0.14
     part
    -0.13
    ç³»
    -0.13
     дело
    -0.13
    ário
    -0.13
    pu
    -0.12
    POSITIVE LOGITS
     Recent
    0.18
    æľĢè¿ij
    0.17
     recent
    0.17
     presently
    0.17
     currently
    0.17
    Currently
    0.15
    marvin
    0.15
    Recent
    0.15
    currently
    0.15
     ÑĤекÑĥÑī
    0.15
    Activations Density 0.009%

    No Known Activations