© 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. 107008
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to people and objects

    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
    iba
    -0.07
    è²´
    -0.06
     savoir
    -0.06
    å¨ĺ
    -0.06
     Pars
    -0.06
    allon
    -0.06
     NavParams
    -0.06
    alez
    -0.06
    rimp
    -0.06
    ivement
    -0.06
    POSITIVE LOGITS
    afka
    0.07
    IPHER
    0.06
    UBL
    0.06
    /GPL
    0.06
     Protest
    0.06
    ostel
    0.06
    ITTE
    0.06
    -scalable
    0.06
    UniqueId
    0.06
    ziel
    0.06
    Activations Density 0.000%

    No Known Activations