© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 76189
    Prev
    Next
    INDEX
    Explanations

    words related to describing and categorizing

    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
    aliz
    -0.08
    ardu
    -0.08
    rada
    -0.07
    ắt
    -0.07
    tdown
    -0.07
    olio
    -0.07
    olis
    -0.07
    uevo
    -0.07
    alie
    -0.07
    vana
    -0.07
    POSITIVE LOGITS
    ãģķãģĦ
    0.06
     sol
    0.06
     default
    0.06
     and
    0.06
     wine
    0.06
     Yak
    0.06
     Wr
    0.05
     اÙĦاØŃ
    0.05
     lines
    0.05
     hab
    0.05
    Activations Density 0.000%

    No Known Activations