© 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. 22-LLAMASCOPE-RES-131K
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    references to publications or printed materials

    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
     Furn
    -0.07
    urm
    -0.07
    ild
    -0.06
     complication
    -0.06
    ho
    -0.06
    ุร
    -0.06
    icap
    -0.06
    alm
    -0.06
     sm
    -0.06
    esh
    -0.06
    POSITIVE LOGITS
    é¼»
    0.07
    æ¦
    0.07
    stral
    0.06
    esinin
    0.06
    zure
    0.06
    ì§ĢëıĦ
    0.06
     Kaf
    0.06
     guarda
    0.06
    strap
    0.06
    Sensitive
    0.06
    Activations Density 0.000%

    No Known Activations