© 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. 129114
    Prev
    Next
    INDEX
    Explanations

    references or discussions about life experiences

    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
    Trademark
    -0.07
    crap
    -0.06
    arme
    -0.06
    afc
    -0.06
    unsch
    -0.06
    izzard
    -0.06
     Kral
    -0.06
    ihn
    -0.06
    ض
    -0.06
    oria
    -0.06
    POSITIVE LOGITS
    /world
    0.07
    stem
    0.07
    /company
    0.06
    ocket
    0.06
    aggi
    0.06
    าว
    0.06
    ümÃ¼ÅŁ
    0.06
    .getColumnIndex
    0.06
    /dom
    0.06
    nar
    0.06
    Activations Density 0.016%

    No Known Activations