© 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. 9-LLAMASCOPE-RES-131K
    11. 95652
    Prev
    Next
    INDEX
    Explanations

    terms related to surveillance and data security

    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
     Identifier
    -0.07
    ARSER
    -0.07
    ¹Ħ
    -0.07
    askan
    -0.07
    atcher
    -0.07
    ender
    -0.07
    ungan
    -0.07
    иÑı
    -0.07
    adio
    -0.07
    .kode
    -0.06
    POSITIVE LOGITS
    anova
    0.06
    Łèĥ½
    0.06
     distant
    0.06
    unci
    0.06
     Campos
    0.05
    dbl
    0.05
    bbb
    0.05
    iw
    0.05
    riere
    0.05
     distance
    0.05
    Activations Density 0.001%

    No Known Activations