© 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. 26867
    Prev
    Next
    INDEX
    Explanations

    identifiers related to academic or scientific publications

    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
     univers
    -0.06
    act
    -0.06
    ockey
    -0.06
    uard
    -0.06
    :
    -0.06
     Snap
    -0.05
     propulsion
    -0.05
    k
    -0.05
    Ñĥж
    -0.05
     Dar
    -0.05
    POSITIVE LOGITS
    ityEngine
    0.09
    elts
    0.08
    edImage
    0.07
    issant
    0.07
    Sharper
    0.07
    Inspectable
    0.07
    ControlItem
    0.07
    едини
    0.07
    landa
    0.07
    FirstResponder
    0.07
    Activations Density 0.001%

    No Known Activations