© 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. 74907
    Prev
    Next
    INDEX
    Explanations

    references to a geographic feature which may have been mentioned previously

    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
    .CV
    -0.09
    ngr
    -0.08
     Åĵ
    -0.07
    нин
    -0.07
    /rss
    -0.07
    ová
    -0.07
    ãĥ³ãĥĶ
    -0.07
    nof
    -0.07
    Ùĩ
    -0.07
    жÑĥ
    -0.07
    POSITIVE LOGITS
    101
    0.06
    ugu
    0.06
    pler
    0.06
    utin
    0.06
    419
    0.05
     PS
    0.05
    alie
    0.05
    leftright
    0.05
    Ĺ
    0.05
    001
    0.05
    Activations Density 0.048%

    No Known Activations