© 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. 74859
    Prev
    Next
    INDEX
    Explanations

    time-related information and scheduling details

    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
    èª
    -0.08
    anny
    -0.07
    rove
    -0.07
    hdl
    -0.07
    ambio
    -0.07
    enny
    -0.07
    inyin
    -0.07
    ernen
    -0.06
    amu
    -0.06
    uestion
    -0.06
    POSITIVE LOGITS
    /OR
    0.07
     bubb
    0.07
     Cond
    0.06
    lernen
    0.05
     Giov
    0.05
    AuthToken
    0.05
    OTA
    0.05
    LoginPage
    0.05
    iggers
    0.05
    172
    0.05
    Activations Density 0.001%

    No Known Activations