© 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. 17-LLAMASCOPE-RES-131K
    6. 76672
    Prev
    Next
    INDEX
    Explanations

    references to personal background information and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lesia
    -0.08
    _exempt
    -0.07
    witter
    -0.07
    PILE
    -0.07
    appable
    -0.06
    ragen
    -0.06
    æ¡Ī
    -0.06
    queues
    -0.06
    ubl
    -0.06
    aniel
    -0.06
    POSITIVE LOGITS
    buz
    0.07
    enders
    0.07
    .bs
    0.06
     Wand
    0.06
    VN
    0.06
     componentDid
    0.06
    eyse
    0.06
     пеÑĢе
    0.05
    CM
    0.05
    .IsNull
    0.05
    Activations Density 0.001%

    No Known Activations