© 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. 60707
    Prev
    Next
    INDEX
    Explanations

    references to the concept of release or freedom from imprisonment or custody

    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
    ÏĥÏĦά
    -0.07
     ØŃÙĪÙĦ
    -0.07
    äº
    -0.07
    drag
    -0.07
    276
    -0.06
    ulos
    -0.06
    ÑĨÑĮ
    -0.06
    PROTO
    -0.06
    ìĤ¼
    -0.06
    /pdf
    -0.06
    POSITIVE LOGITS
     Release
    0.09
     release
    0.08
     khá»ıi
    0.07
    Release
    0.07
     RELEASE
    0.07
    .Release
    0.07
    /release
    0.07
     after
    0.07
    éĩĬ
    0.07
     releases
    0.06
    Activations Density 0.007%

    No Known Activations