© 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. 126046
    Prev
    Next
    INDEX
    Explanations

    references to licenses and legal agreements

    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
     Feld
    -0.07
    erb
    -0.06
    lander
    -0.06
     synonymous
    -0.06
     sund
    -0.06
    roller
    -0.05
     liberty
    -0.05
     highest
    -0.05
    etak
    -0.05
    ductor
    -0.05
    POSITIVE LOGITS
    opoulos
    0.08
    ulumi
    0.07
    iram
    0.07
    SKTOP
    0.07
    aleb
    0.07
    edImage
    0.07
    ovacÃŃ
    0.07
     Kenn
    0.07
    loser
    0.07
    hift
    0.07
    Activations Density 0.007%

    No Known Activations