© 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. 915
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code structure

    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
    hausen
    -0.07
    roat
    -0.07
    asil
    -0.06
    illard
    -0.06
    legg
    -0.06
    วà¸Ļ
    -0.06
     WOW
    -0.06
    ensis
    -0.06
    áp
    -0.06
     series
    -0.06
    POSITIVE LOGITS
    suspend
    0.07
    utsch
    0.07
    .gdx
    0.07
    maz
    0.07
    SizeMode
    0.07
    DataExchange
    0.06
    BuilderFactory
    0.06
    _tac
    0.06
    364
    0.06
    CrLf
    0.06
    Activations Density 0.114%

    No Known Activations