© 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. 17-LLAMASCOPE-RES-131K
    11. 84034
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for further engagement

    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
    arov
    -0.07
    arios
    -0.06
    ÄIJT
    -0.06
    rant
    -0.06
    atab
    -0.06
    pon
    -0.06
    INU
    -0.06
    _Current
    -0.06
     domicile
    -0.06
    OLS
    -0.05
    POSITIVE LOGITS
     HERE
    0.08
    ypass
    0.08
    lap
    0.07
    skirts
    0.07
    tep
    0.06
    ÃŃst
    0.06
     here
    0.06
    weathermap
    0.06
    overy
    0.06
    here
    0.06
    Activations Density 0.008%

    No Known Activations