© 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. 3411
    Prev
    Next
    INDEX
    Explanations

    references to community support and resources

    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
    yps
    -0.06
    ov
    -0.06
    eyer
    -0.05
     åı
    -0.05
    à¤Ĥà¤ĺ
    -0.05
    egas
    -0.05
     Consumer
    -0.05
    ipple
    -0.05
     pov
    -0.05
    اÙĬا
    -0.05
    POSITIVE LOGITS
     ourselves
    0.10
     our
    0.09
     naše
    0.08
     nosso
    0.08
    Ĺ
    0.08
    æĪij们çļĦ
    0.08
     наÑĪиÑħ
    0.07
     nostro
    0.07
    avou
    0.07
     našich
    0.07
    Activations Density 0.046%

    No Known Activations