© 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. 61625
    Prev
    Next
    INDEX
    Explanations

    elements related to estimation and guessing based on subjective opinions

    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
    chner
    -0.06
     Defender
    -0.06
    ocus
    -0.06
    ttl
    -0.06
    essaging
    -0.05
    .tbl
    -0.05
    zsche
    -0.05
     Tut
    -0.05
     fully
    -0.05
     defenders
    -0.05
    POSITIVE LOGITS
    based
    0.08
     based
    0.08
     uncert
    0.08
     Based
    0.08
    Based
    0.08
    -based
    0.08
    _based
    0.08
    rather
    0.07
    unsupported
    0.07
    -Based
    0.07
    Activations Density 0.034%

    No Known Activations