© 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. 103833
    Prev
    Next
    INDEX
    Explanations

    locations in the form of "based" phrases indicating geographic origins or affiliations

    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
    odel
    -0.07
    feld
    -0.07
    oust
    -0.07
    emoc
    -0.07
    efa
    -0.07
    eres
    -0.07
    arium
    -0.07
    _BORDER
    -0.07
    asp
    -0.07
    abin
    -0.07
    POSITIVE LOGITS
    upon
    0.08
    655
    0.07
     रहन
    0.06
    ãĥĬãĥ¼
    0.06
    phen
    0.06
    CDATA
    0.06
    most
    0.06
    PopupMenu
    0.06
    isode
    0.05
    ê·¼
    0.05
    Activations Density 0.005%

    No Known Activations