Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 118811
    Prev
    Next
    INDEX
    Explanations

    statistics related to demographics and household composition

    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
    Pitch
    -0.07
     Pitch
    -0.07
    utherford
    -0.07
    auga
    -0.07
    orners
    -0.07
    StdString
    -0.07
    erno
    -0.07
     pitch
    -0.07
    ikut
    -0.07
    agt
    -0.07
    POSITIVE LOGITS
    åķĬåķĬ
    0.07
    REEN
    0.06
    ann
    0.06
    iy
    0.06
    fest
    0.06
    zon
    0.06
    aux
    0.06
    fant
    0.06
     Indones
    0.06
    evi
    0.06
    Activations Density 0.004%

    No Known Activations