© 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. 126894
    Prev
    Next
    INDEX
    Explanations

    references to significant numerical data or statistics

    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
    atham
    -0.07
    speech
    -0.06
    721
    -0.06
    ogr
    -0.06
     Hlav
    -0.06
    Reporter
    -0.06
     MacDonald
    -0.06
    oud
    -0.06
    ethe
    -0.06
    ÙĦÛĮس
    -0.06
    POSITIVE LOGITS
    AFP
    0.08
    utos
    0.08
     AFP
    0.08
    anj
    0.07
    /AFP
    0.07
     US
    0.06
     Corporate
    0.06
    alloca
    0.06
     harmless
    0.06
     Coff
    0.06
    Activations Density 0.029%

    No Known Activations