© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 6811
    Prev
    Next
    INDEX
    Explanations

    references to sports achievements and athlete performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otal
    -0.16
    _singleton
    -0.15
    etsk
    -0.15
    è¤
    -0.15
    utow
    -0.15
    elu
    -0.14
    inaire
    -0.14
    assa
    -0.14
    Ñģли
    -0.14
    REFERRED
    -0.13
    POSITIVE LOGITS
     senior
    0.87
     Senior
    0.72
     junior
    0.71
     sophomore
    0.66
     Soph
    0.66
    Senior
    0.65
     seniors
    0.65
    sen
    0.57
     soph
    0.57
     Junior
    0.55
    Activations Density 0.174%

    No Known Activations