© 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. 106876
    Prev
    Next
    INDEX
    Explanations

    references to rights and reservations

    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
    avail
    -0.08
    upplier
    -0.08
    ERM
    -0.07
    yz
    -0.07
    emez
    -0.07
    unlock
    -0.06
    yb
    -0.06
    presso
    -0.06
     Machinery
    -0.06
    zÃŃ
    -0.06
    POSITIVE LOGITS
     reserve
    0.09
     reserves
    0.09
     Reserve
    0.09
     reserved
    0.08
     Reserved
    0.07
     rights
    0.07
    Reserved
    0.07
     reserv
    0.07
     space
    0.07
    /res
    0.07
    Activations Density 0.004%

    No Known Activations