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. 17-LLAMASCOPE-RES-32K
    6. 21500
    Prev
    Next
    INDEX
    Explanations

    numeric identifiers or codes related to books or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olley
    -0.16
    azine
    -0.15
    hee
    -0.15
    NEL
    -0.15
    adel
    -0.15
    azon
    -0.15
    acman
    -0.15
     Äijá»ĵng
    -0.14
    ظ
    -0.14
    atively
    -0.14
    POSITIVE LOGITS
    een
    0.21
    ãģªãģı
    0.19
    nÃŃ
    0.19
    als
    0.18
    íĿ¬
    0.17
    иÑħ
    0.16
    eenth
    0.15
    eken
    0.15
    \Eloquent
    0.15
    न
    0.15
    Activations Density 0.091%

    No Known Activations