© 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. 118624
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and landmarks

    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
     Shore
    -0.06
    iber
    -0.06
    äºĭæĥħ
    -0.05
    ijd
    -0.05
    ò
    -0.05
    lak
    -0.05
    arma
    -0.05
     wrong
    -0.05
    iv
    -0.05
     Cyr
    -0.05
    POSITIVE LOGITS
     city
    0.09
    city
    0.08
    ucken
    0.08
     #__
    0.07
    aru
    0.07
    Vir
    0.07
    .cgi
    0.07
    ãĤħ
    0.07
    hlas
    0.07
    gili
    0.07
    Activations Density 0.028%

    No Known Activations