© 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. 128983
    Prev
    Next
    INDEX
    Explanations

    references to academic evaluations or assessments

    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
    avior
    -0.07
    åĸĶ
    -0.06
    ï¼
    -0.06
    prites
    -0.06
     advisor
    -0.06
    коз
    -0.06
    nun
    -0.06
    igor
    -0.06
    898
    -0.06
    463
    -0.06
    POSITIVE LOGITS
     centrif
    0.06
    coni
    0.06
     thẩm
    0.06
     numberWith
    0.06
     osm
    0.06
    ured
    0.06
    hlen
    0.06
    ambre
    0.06
    stin
    0.06
    ames
    0.06
    Activations Density 0.000%

    No Known Activations