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

    Neuronpedia

    APICircuit 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. 7-LLAMASCOPE-RES-32K
    6. 22267
    Prev
    Next
    INDEX
    Explanations

    mentions of financial quarters and reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .jquery
    -0.16
    elu
    -0.16
    zc
    -0.15
     Bened
    -0.15
    žÃŃ
    -0.15
    ilk
    -0.14
    ãģ£ãģį
    -0.14
    inker
    -0.14
    nist
    -0.14
    umas
    -0.14
    POSITIVE LOGITS
    umb
    0.16
    èģ
    0.15
    istrovstvÃŃ
    0.15
    æ¹
    0.14
    ambique
    0.14
    maal
    0.14
    HL
    0.14
    925
    0.14
    łí
    0.14
    sn
    0.14
    Activations Density 0.016%

    No Known Activations