© 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. 103801
    Prev
    Next
    INDEX
    Explanations

    instructions related to actions or methods for achieving specific outcomes

    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
    SYM
    -0.07
    bris
    -0.07
    iale
    -0.06
    udos
    -0.06
    ibus
    -0.06
    idel
    -0.06
    æĪIJäºĨ
    -0.06
    plr
    -0.06
    Ĥæķ°
    -0.06
    ycz
    -0.06
    POSITIVE LOGITS
     Sil
    0.06
     get
    0.06
    rix
    0.06
    Sil
    0.06
    celik
    0.06
     Malcolm
    0.06
     $("#"
    0.06
    opis
    0.06
     Midnight
    0.06
    ung
    0.06
    Activations Density 0.011%

    No Known Activations