© 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. 15-LLAMASCOPE-RES-131K
    6. 677
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "ginger."

    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
     Bott
    -0.06
    ouns
    -0.06
    sing
    -0.06
    LU
    -0.06
     Dort
    -0.06
    udiant
    -0.06
    OrCreate
    -0.06
    atics
    -0.06
    sie
    -0.06
    melon
    -0.06
    POSITIVE LOGITS
    bread
    0.07
     huyết
    0.07
    kins
    0.07
    emma
    0.07
    roke
    0.07
    erman
    0.07
    iek
    0.06
    á»ģn
    0.06
    ÄĽÅĻ
    0.06
    lic
    0.06
    Activations Density 0.004%

    No Known Activations