© 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. 125851
    Prev
    Next
    INDEX
    Explanations

    occurrences of contrasting or conditional phrases

    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
    isky
    -0.07
    /Dk
    -0.07
     Favorites
    -0.06
    enegro
    -0.06
    ILES
    -0.06
    .pa
    -0.06
    imore
    -0.06
    aliases
    -0.06
     Picker
    -0.06
    egral
    -0.06
    POSITIVE LOGITS
    -ing
    0.07
    ledi
    0.06
    ody
    0.06
    è¤
    0.06
    adding
    0.06
    .addProperty
    0.06
    epy
    0.06
    Pel
    0.06
    (SC
    0.06
    ůl
    0.06
    Activations Density 0.005%

    No Known Activations