© 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. 40823
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate key information or discussions related to various topics

    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
     countless
    -0.07
     numerous
    -0.07
     lots
    -0.07
     unspecified
    -0.06
     Numerous
    -0.06
     many
    -0.06
     hundreds
    -0.06
    .sl
    -0.06
     Heg
    -0.06
    eg
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.11
     typical
    0.08
    ivé
    0.08
    ÑĤÑĢо
    0.08
    /***/
    0.08
    fone
    0.08
    typ
    0.07
     myself
    0.07
    undler
    0.07
     meiner
    0.07
    Activations Density 0.069%

    No Known Activations