© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40508
    Prev
    Next
    INDEX
    Explanations

    reported speech and dialogue phrases

    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
    ething
    -0.08
    ustos
    -0.08
    SPATH
    -0.08
    با
    -0.08
    ležit
    -0.08
    Ħìŀ¬
    -0.07
    laden
    -0.07
    çīĩ
    -0.07
    ColumnsMode
    -0.07
    eft
    -0.07
    POSITIVE LOGITS
    :
    0.08
     '
    0.06
    eger
    0.06
     ->
    0.06
    nic
    0.06
     num
    0.06
    ->
    0.06
    ajo
    0.06
     >>
    0.06
    atten
    0.06
    Activations Density 0.027%

    No Known Activations