© 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. 78233
    Prev
    Next
    INDEX
    Explanations

    concepts related to dimensions, qualities, and methods of measurement

    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
    ilig
    -0.08
    onga
    -0.07
    rone
    -0.07
    ault
    -0.07
    ома
    -0.07
     davon
    -0.07
    amac
    -0.07
    illac
    -0.07
    atif
    -0.07
    iais
    -0.06
    POSITIVE LOGITS
     of
    0.08
     that
    0.07
     tú
    0.06
     required
    0.06
    .resources
    0.06
    vat
    0.06
     demanded
    0.06
     inst
    0.06
     summ
    0.06
     prescribed
    0.06
    Activations Density 0.042%

    No Known Activations