Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3621
    Prev
    Next
    INDEX
    Explanations

    common articles and prepositions in the text

    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
    ?option
    -0.08
     nonatomic
    -0.08
    ContentLoaded
    -0.08
    _________________↵↵
    -0.08
    ¶Į
    -0.07
    ¦æĥħ
    -0.07
    _AP
    -0.07
    оÑģÑĤ
    -0.07
    SError
    -0.07
    "data
    -0.07
    POSITIVE LOGITS
    Question
    0.06
    ATE
    0.06
    lick
    0.06
    iform
    0.06
    orem
    0.06
    .
    0.06
    a
    0.06
    ittel
    0.06
    uele
    0.05
    oretical
    0.05
    Activations Density 0.000%

    No Known Activations