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. 118702
    Prev
    Next
    INDEX
    Explanations

    terms related to psychological concepts and analysis

    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
     Dut
    -0.07
    kowski
    -0.07
     Sahara
    -0.06
    enton
    -0.06
    .hot
    -0.06
    xing
    -0.06
    Ỽt
    -0.06
    Ãło
    -0.06
     translucent
    -0.06
    jar
    -0.06
    POSITIVE LOGITS
     Freud
    0.09
     incest
    0.07
     Klein
    0.07
     Bowl
    0.07
     analyst
    0.07
     ph
    0.07
     klein
    0.07
    ÏĨι
    0.07
     analytic
    0.07
    ettel
    0.07
    Activations Density 0.054%

    No Known Activations