© 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. 5-LLAMASCOPE-RES-131K
    11. 126544
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a strong argument or case for a particular idea or action

    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
    as
    -0.07
     Sac
    -0.06
    orks
    -0.06
    sse
    -0.06
    åŀ
    -0.06
     afford
    -0.06
    Ŀ
    -0.05
    ulaire
    -0.05
    a
    -0.05
    aff
    -0.05
    POSITIVE LOGITS
    iêu
    0.08
    ulumi
    0.08
    GetPosition
    0.07
    áo
    0.07
    wargs
    0.07
    éri
    0.07
    .calendar
    0.07
    BeNull
    0.07
    ocache
    0.07
    laus
    0.07
    Activations Density 0.004%

    No Known Activations