© 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. 56306
    Prev
    Next
    INDEX
    Explanations

    expressions related to sharing and promoting content

    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
    oring
    -0.08
     fur
    -0.07
    ariat
    -0.07
    okus
    -0.07
     Fur
    -0.07
    lok
    -0.06
     Enhancement
    -0.06
    ç´Ģ
    -0.06
    ush
    -0.06
     Egg
    -0.06
    POSITIVE LOGITS
    omanip
    0.06
    illos
    0.06
    .connect
    0.06
    æ´¾
    0.06
    inis
    0.06
    _ue
    0.06
    nid
    0.06
    -thumbnails
    0.06
    eniable
    0.06
    apore
    0.06
    Activations Density 0.001%

    No Known Activations