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. 8-LLAMASCOPE-RES-32K
    6. 7724
    Prev
    Next
    INDEX
    Explanations

    instances of action and interaction, particularly those involving physical sensations and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riba
    -0.15
    sted
    -0.15
    ccione
    -0.15
    ilan
    -0.15
    lacak
    -0.14
    raç
    -0.14
     populous
    -0.13
    isku
    -0.13
    roperty
    -0.13
    ibbon
    -0.13
    POSITIVE LOGITS
     Gratuit
    0.15
     Annunci
    0.13
    ÙĪÙĬس
    0.12
    (Boolean
    0.12
    =nil
    0.12
     lays
    0.12
     è©ķ価
    0.12
     shemale
    0.12
    _nf
    0.12
     anale
    0.12
    Activations Density 0.123%

    No Known Activations