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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96237
    Prev
    Next
    INDEX
    Explanations

    instances of displacement or leaving one's home or belongings behind

    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
    bern
    -0.07
    109
    -0.07
    ano
    -0.07
    eor
    -0.07
    faces
    -0.06
    uka
    -0.06
    ali
    -0.06
    elight
    -0.06
    bject
    -0.06
    rais
    -0.06
    POSITIVE LOGITS
    WD
    0.08
     Lebens
    0.06
    /*/
    0.06
     táºŃn
    0.06
     khá»ıi
    0.06
    .imag
    0.06
    istributor
    0.06
    .jd
    0.06
    äºķ
    0.06
    .LayoutStyle
    0.06
    Activations Density 0.029%

    No Known Activations