© 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. 90184
    Prev
    Next
    INDEX
    Explanations

    phrases that convey a sense of balance and moderation

    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
    ir
    -0.07
    prung
    -0.07
    baugh
    -0.07
    tempt
    -0.07
    nt
    -0.06
    eza
    -0.06
    /OR
    -0.06
    975
    -0.06
    chg
    -0.06
    ált
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.08
    -sort
    0.07
    许
    0.07
    coli
    0.07
    /all
    0.07
    ëģĶ
    0.07
    ansi
    0.06
     ÙħÙħا
    0.06
    ABEL
    0.06
     bit
    0.06
    Activations Density 0.005%

    No Known Activations