© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62337
    Prev
    Next
    INDEX
    Explanations

    political party affiliations and their leaders

    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
    ajÄħ
    -0.07
    enden
    -0.07
    fork
    -0.07
    umor
    -0.07
    reb
    -0.07
     geil
    -0.07
    inz
    -0.06
    _bootstrap
    -0.06
    ltr
    -0.06
     полÑĥ
    -0.06
    POSITIVE LOGITS
     Party
    0.11
     party
    0.09
    Party
    0.07
     PARTY
    0.07
     leader
    0.07
    ambi
    0.07
    urity
    0.07
    -controlled
    0.07
    -run
    0.06
    party
    0.06
    Activations Density 0.028%

    No Known Activations