© 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. 27053
    Prev
    Next
    INDEX
    Explanations

    components of programming code or annotations related to it

    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
    evin
    -0.07
    altung
    -0.07
    rella
    -0.07
    deÅŁ
    -0.07
    azzi
    -0.07
    axter
    -0.07
    peria
    -0.07
    ubber
    -0.06
    ocaly
    -0.06
    afb
    -0.06
    POSITIVE LOGITS
    eman
    0.07
    ÑĢиÑģ
    0.06
    ãĤĵãģ©
    0.06
    åħ°
    0.06
     Exped
    0.06
    igne
    0.06
    gan
    0.05
     XCT
    0.05
     const
    0.05
    jec
    0.05
    Activations Density 0.000%

    No Known Activations