© 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. 57134
    Prev
    Next
    INDEX
    Explanations

    measurements related to distance and location

    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
    arkin
    -0.08
    ullan
    -0.07
    .fhir
    -0.07
    akt
    -0.06
    /stdc
    -0.06
    ays
    -0.06
    /vnd
    -0.06
    icha
    -0.06
    ffffffff
    -0.06
    _HW
    -0.06
    POSITIVE LOGITS
    onaut
    0.06
    gency
    0.06
    Co
    0.06
    longleftrightarrow
    0.06
    ãģ®ãģ«
    0.06
    PU
    0.06
     Prev
    0.06
    ensively
    0.06
    ryo
    0.06
    guard
    0.05
    Activations Density 0.000%

    No Known Activations