© 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. 29512
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to video formats and subtitle file types

    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
     branch
    -0.07
    ç²Ĺ
    -0.07
     Branch
    -0.06
    branch
    -0.06
    icha
    -0.06
     deep
    -0.06
     branches
    -0.06
    bn
    -0.05
     on
    -0.05
     faced
    -0.05
    POSITIVE LOGITS
     format
    0.10
     formato
    0.09
    .usermodel
    0.09
    rypted
    0.09
     Format
    0.08
    CLUDING
    0.08
    ysize
    0.08
    -format
    0.08
    FormatException
    0.08
     gz
    0.08
    Activations Density 0.034%

    No Known Activations