© 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. 94148
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reliance or dependence on external methods or solutions

    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
    оÑĤÑĮ
    -0.07
    rede
    -0.07
    ninger
    -0.06
    inou
    -0.06
    baum
    -0.06
    NING
    -0.06
    ni
    -0.06
    ReadOnly
    -0.06
    awy
    -0.06
    ãĥ¼ãĥIJ
    -0.06
    POSITIVE LOGITS
     tactics
    0.07
    ezier
    0.07
    $MESS
    0.07
    879
    0.07
    UILayout
    0.06
    937
    0.06
    /include
    0.06
     recourse
    0.06
    TargetException
    0.06
    ิà¸ĸ
    0.06
    Activations Density 0.003%

    No Known Activations