© 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. 29637
    Prev
    Next
    INDEX
    Explanations

    the presence of location or area names

    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
     Dawson
    -0.06
    amat
    -0.06
    dit
    -0.06
    irá
    -0.05
    anya
    -0.05
    ográf
    -0.05
    ney
    -0.05
     correspondence
    -0.05
     آذ
    -0.05
    ascade
    -0.05
    POSITIVE LOGITS
     town
    0.08
    osu
    0.08
     city
    0.08
     area
    0.07
    asher
    0.07
    cka
    0.07
    üzel
    0.07
     Kostenlose
    0.07
    usan
    0.07
     Butter
    0.07
    Activations Density 0.015%

    No Known Activations