© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    common terms and concepts associated with commonality or shared attributes

    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
    ern
    -0.07
    ronics
    -0.07
    ic
    -0.07
    hta
    -0.07
    idel
    -0.07
    ray
    -0.06
    go
    -0.06
    κÎŃ
    -0.06
    bestos
    -0.06
    gos
    -0.06
    POSITIVE LOGITS
    wealth
    0.16
     denominator
    0.11
    ality
    0.10
    /common
    0.10
    place
    0.10
    /Common
    0.10
    places
    0.09
    est
    0.09
    alty
    0.09
    alties
    0.08
    Activations Density 0.021%

    No Known Activations