© 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. 78719
    Prev
    Next
    INDEX
    Explanations

    expressions of understanding and awareness regarding needs and values

    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
    //{{
    -0.06
    вий
    -0.06
    iece
    -0.06
     Cro
    -0.06
    dden
    -0.06
    lier
    -0.06
     Evening
    -0.06
    äºŃ
    -0.06
    aston
    -0.06
    umbo
    -0.06
    POSITIVE LOGITS
    ooks
    0.07
    lege
    0.07
    768
    0.06
    ülü
    0.06
    ANGO
    0.06
    óc
    0.06
    REEN
    0.06
    bones
    0.06
    /MIT
    0.06
    aska
    0.06
    Activations Density 0.009%

    No Known Activations