© 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. 636
    Prev
    Next
    INDEX
    Explanations

    content related to community leadership and prevention strategies

    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
    obao
    -0.08
    ngr
    -0.08
     имÑĥ
    -0.07
    abbo
    -0.07
    ucene
    -0.07
    ubic
    -0.07
    ujet
    -0.07
     Hath
    -0.07
    coc
    -0.07
    pla
    -0.07
    POSITIVE LOGITS
    690
    0.06
    ipur
    0.06
    ONGL
    0.06
     [âĢ¦
    0.06
     Honour
    0.06
    855
    0.06
    614
    0.06
     {?>↵
    0.05
    664
    0.05
    VERTISEMENT
    0.05
    Activations Density 0.009%

    No Known Activations