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. 3525
    Prev
    Next
    INDEX
    Explanations

    conjunctions that connect ideas or phrases within a text

    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
    ngo
    -0.09
    ư
    -0.08
    flen
    -0.08
    urette
    -0.08
    bero
    -0.08
    à¤ľà¤¹
    -0.08
    arella
    -0.07
    .Override
    -0.07
    /frontend
    -0.07
    enido
    -0.07
    POSITIVE LOGITS
     thereby
    0.08
    Beans
    0.06
     highly
    0.05
    arl
    0.05
    CLUDING
    0.05
     themselves
    0.05
    nev
    0.05
    azel
    0.05
     prosperity
    0.05
    AA
    0.05
    Activations Density 0.101%

    No Known Activations