© 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. 106986
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and inquiries with representatives or service providers

    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
    ylon
    -0.06
    unning
    -0.06
     Favor
    -0.06
    alf
    -0.06
    inges
    -0.06
    ersist
    -0.06
    imoto
    -0.06
    å±ŀ
    -0.06
     theirs
    -0.06
    antom
    -0.06
    POSITIVE LOGITS
    stup
    0.08
    iors
    0.07
    olean
    0.07
    ãĥ³ãĥĸ
    0.07
    UnitOfWork
    0.07
    оÑĢо
    0.07
    stras
    0.06
    .masks
    0.06
    curities
    0.06
     nackte
    0.06
    Activations Density 0.000%

    No Known Activations