© 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. 57516
    Prev
    Next
    INDEX
    Explanations

    expressions indicating necessity or recommendations related to tasks and proposals

    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
    /stdc
    -0.09
    732
    -0.08
    Ĭ¶
    -0.08
    resco
    -0.07
    EdgeInsets
    -0.07
    áv
    -0.07
    ableOpacity
    -0.07
    ardash
    -0.07
    esktop
    -0.07
    ofday
    -0.06
    POSITIVE LOGITS
    sing
    0.07
    athi
    0.06
    HAND
    0.06
     Civ
    0.06
    omat
    0.06
    ork
    0.06
    iri
    0.06
    unlink
    0.06
    vant
    0.06
    olding
    0.06
    Activations Density 0.012%

    No Known Activations