© 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. 15-LLAMASCOPE-RES-131K
    11. 103987
    Prev
    Next
    INDEX
    Explanations

    terms related to selections and eligibility criteria for programs or listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Connecting words and phrases that link subjects to their descriptions or attributes in informational and explanatory text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    reau
    -0.06
    erson
    -0.06
    _exempt
    -0.06
     baise
    -0.06
     имÑĥ
    -0.06
    ponent
    -0.05
    owell
    -0.05
     Suff
    -0.05
    ÎķÎļ
    -0.05
    croft
    -0.05
    POSITIVE LOGITS
    deme
    0.07
    quam
    0.07
    ospace
    0.07
    .Ship
    0.06
    )const
    0.06
    arel
    0.06
    Filled
    0.06
    AVIS
    0.06
    DEM
    0.06
    .Dev
    0.06
    Activations Density 0.006%

    No Known Activations