© 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. 57677
    Prev
    Next
    INDEX
    Explanations

    instances and conditions related to timing or circumstances for actions

    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
    iene
    -0.06
    peon
    -0.06
    icz
    -0.06
    idd
    -0.06
    oser
    -0.06
     Pais
    -0.06
    kas
    -0.05
    agal
    -0.05
    aney
    -0.05
    _notify
    -0.05
    POSITIVE LOGITS
     æ°¸
    0.07
    erence
    0.07
    ird
    0.07
    .Glide
    0.07
     trying
    0.07
    azen
    0.07
    uct
    0.07
    ROLS
    0.07
    IRD
    0.06
    uctor
    0.06
    Activations Density 0.027%

    No Known Activations