© 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. 3982
    Prev
    Next
    INDEX
    Explanations

    words related to specific names or brands within the context of discussions

    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
    ustum
    -0.08
    alet
    -0.07
    eson
    -0.07
    nila
    -0.07
    ================================================================
    -0.07
    yle
    -0.07
    reements
    -0.07
    ÄIJT
    -0.06
    unbind
    -0.06
    ainen
    -0.06
    POSITIVE LOGITS
    ness
    0.07
    gets
    0.07
     conv
    0.06
    ful
    0.06
    riel
    0.06
    anken
    0.06
    iot
    0.06
    ets
    0.06
    (mut
    0.06
    sm
    0.06
    Activations Density 0.012%

    No Known Activations