© 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. 71152
    Prev
    Next
    INDEX
    Explanations

    language around decision-making and personal choices

    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
    ISH
    -0.07
    ÌĨ
    -0.07
    ÙĪارÙĩ
    -0.06
    iaux
    -0.06
     Grimm
    -0.06
    .sys
    -0.06
    ERING
    -0.06
    WithMany
    -0.06
    OPY
    -0.06
    oku
    -0.06
    POSITIVE LOGITS
    uchs
    0.07
    apon
    0.07
     Trial
    0.07
    ogue
    0.07
    oref
    0.07
    ucha
    0.07
     UNUSED
    0.06
    .flink
    0.06
     Meh
    0.06
    erson
    0.06
    Activations Density 0.016%

    No Known Activations