Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118705
    Prev
    Next
    INDEX
    Explanations

    political references and elements related to competition or contention

    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
    bast
    -0.07
     Cald
    -0.06
     Bast
    -0.06
    atern
    -0.06
    Streamer
    -0.06
    áf
    -0.06
    edula
    -0.06
    åij
    -0.06
     Opinion
    -0.06
    plet
    -0.06
    POSITIVE LOGITS
     anytime
    0.12
     any
    0.11
    any
    0.10
     ANY
    0.10
     Any
    0.09
    Any
    0.09
     anybody
    0.09
    ä»»ä½ķ
    0.08
    .any
    0.08
    (any
    0.08
    Activations Density 0.020%

    No Known Activations