© 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. 76898
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "following."

    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
    eres
    -0.08
    ninger
    -0.07
    bn
    -0.07
    monic
    -0.07
     Leone
    -0.06
    pras
    -0.06
    anax
    -0.06
    rowse
    -0.06
    uje
    -0.06
    swers
    -0.06
    POSITIVE LOGITS
     OnTrigger
    0.07
     ActionTypes
    0.07
    akis
    0.07
    egis
    0.07
    ιο
    0.06
    _AB
    0.06
    unfold
    0.06
     unic
    0.06
    och
    0.06
    fram
    0.06
    Activations Density 0.002%

    No Known Activations