© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16186
    Prev
    Next
    INDEX
    Explanations

    mentions of negative life events or personal hardships

    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
    ovel
    -0.07
    ube
    -0.07
    isans
    -0.07
    lett
    -0.06
    utz
    -0.06
    FFE
    -0.06
    rypton
    -0.06
    ipo
    -0.06
     Ãĸl
    -0.06
    غÙĨ
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
    ilden
    0.07
     forever
    0.07
    mada
    0.07
    allo
    0.06
     invasion
    0.06
     morale
    0.06
     Confidence
    0.06
    "urls
    0.06
    ableView
    0.06
    Activations Density 0.013%

    No Known Activations