© 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. 119484
    Prev
    Next
    INDEX
    Explanations

    instances of availability and requests for comments

    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
    avou
    -0.07
    jure
    -0.07
    æľī人
    -0.07
    rompt
    -0.07
    HeaderValue
    -0.07
    alez
    -0.07
    kah
    -0.06
     Astroph
    -0.06
    .BackgroundColor
    -0.06
    wyn
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.07
     comment
    0.07
    dia
    0.06
     opinions
    0.06
    aver
    0.06
    -initial
    0.05
     HIP
    0.05
     quota
    0.05
    UGC
    0.05
    INIT
    0.05
    Activations Density 0.001%

    No Known Activations