© 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. 15-LLAMASCOPE-RES-131K
    11. 90051
    Prev
    Next
    INDEX
    Explanations

    descriptors of luxurious or impressive features

    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
    /
    -0.07
    _
    -0.06
    ingham
    -0.06
    /in
    -0.06
     |
    -0.06
    <|end_of_text|>
    -0.06
     for
    -0.06
     _
    -0.06
     /
    -0.06
     theirs
    -0.06
    POSITIVE LOGITS
     EXEMPLARY
    0.09
    ediÄŁi
    0.09
    /*č↵
    0.09
    'gc
    0.08
    enor
    0.08
    |RF
    0.08
    $MESS
    0.08
    fact
    0.08
    Ãłng
    0.08
    onium
    0.08
    Activations Density 0.020%

    No Known Activations