Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 4009
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mam
    -0.16
    Łèĥ½
    -0.15
    že
    -0.15
    apg
    -0.15
    anton
    -0.15
    TEGR
    -0.14
     authorize
    -0.14
     authorized
    -0.14
    cul
    -0.14
    weeney
    -0.14
    POSITIVE LOGITS
    åºĦ
    0.14
     Force
    0.14
    zer
    0.14
    ytt
    0.14
    rol
    0.14
    ilet
    0.13
    /by
    0.13
    ramework
    0.13
     ti
    0.13
     expend
    0.13
    Activations Density 0.050%

    No Known Activations