© 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. 5-LLAMASCOPE-RES-131K
    11. 125982
    Prev
    Next
    INDEX
    Explanations

    terms related to user agreements and service policies

    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
    sez
    -0.07
    æĬľ
    -0.07
     marsh
    -0.07
    eldorf
    -0.06
     wo
    -0.06
     h
    -0.06
    úa
    -0.06
     ent
    -0.06
     system
    -0.06
     HL
    -0.06
    POSITIVE LOGITS
    åĿĬ
    0.08
    creens
    0.07
    loth
    0.07
    à¹Ĥà¸Ĭ
    0.07
    ót
    0.07
    forcements
    0.07
     دÙģ
    0.06
    áºł
    0.06
    Ùĩار
    0.06
    LESS
    0.06
    Activations Density 0.001%

    No Known Activations