© 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. 55920
    Prev
    Next
    INDEX
    Explanations

    words related to a particular type of individual or characteristic

    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
     Eld
    -0.06
    andle
    -0.06
    IGHLIGHT
    -0.06
     seam
    -0.06
    Ø®ÙĪاÙĨ
    -0.05
    annah
    -0.05
    νά
    -0.05
     prim
    -0.05
    ady
    -0.05
    apult
    -0.05
    POSITIVE LOGITS
    eting
    0.08
    ETING
    0.08
    ìĤ¬íķŃ
    0.07
    å¤ĩ注
    0.07
     Incontri
    0.07
    ety
    0.07
    åŀĤ
    0.07
    etimes
    0.07
    ãĤ¿ãĥ«
    0.07
     ìĤ¬íķŃ
    0.07
    Activations Density 0.001%

    No Known Activations