© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126823
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time progression or continuity

    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
     behalf
    -0.08
     beforeSend
    -0.06
    nap
    -0.06
    ovna
    -0.06
     kir
    -0.06
    uch
    -0.06
     вдÑĢÑĥг
    -0.06
    irsch
    -0.06
     suddenly
    -0.06
     seize
    -0.06
    POSITIVE LOGITS
     then
    0.08
     karak
    0.08
    empre
    0.08
    maal
    0.08
    ÄĽt
    0.07
     Äijó
    0.07
     thereafter
    0.07
    álo
    0.07
    ward
    0.07
    esz
    0.07
    Activations Density 0.009%

    No Known Activations