© 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. 17-LLAMASCOPE-RES-131K
    11. 126786
    Prev
    Next
    INDEX
    Explanations

    terms related to names and titles associated with places and honors

    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
    ivel
    -0.06
    altung
    -0.06
    ainty
    -0.06
    LANG
    -0.06
    ub
    -0.06
    ampler
    -0.06
    ÑĤап
    -0.06
    AMPL
    -0.06
    'icon
    -0.06
    hir
    -0.06
    POSITIVE LOGITS
     name
    0.18
     names
    0.15
     Name
    0.15
    -name
    0.14
    åIJį
    0.14
    name
    0.14
    _name
    0.14
     Names
    0.14
     NAME
    0.13
    Name
    0.13
    Activations Density 0.056%

    No Known Activations