© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106132
    Prev
    Next
    INDEX
    Explanations

    mentions of butter and its variations in different contexts

    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
    spark
    -0.08
    mgr
    -0.08
    üçük
    -0.07
    ropa
    -0.07
    ropdown
    -0.07
    алом
    -0.07
    elijk
    -0.07
    stanbul
    -0.06
    nost
    -0.06
    cheng
    -0.06
    POSITIVE LOGITS
    edImage
    0.09
    combe
    0.08
    cream
    0.07
    entials
    0.07
    oni
    0.07
    flies
    0.07
    .semantic
    0.07
    çĹ
    0.07
    RESSED
    0.07
    lick
    0.06
    Activations Density 0.007%

    No Known Activations