© 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. 17-LLAMASCOPE-RES-131K
    6. 40915
    Prev
    Next
    INDEX
    Explanations

    the word "are" and its variations indicating existence or presence

    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
     Classified
    -0.07
    _inches
    -0.07
    ãĥ¬ãĥ³
    -0.06
    _attribute
    -0.06
    .springboot
    -0.06
    olo
    -0.06
    velle
    -0.06
    .Annotation
    -0.06
    abbit
    -0.06
    etty
    -0.06
    POSITIVE LOGITS
     roman
    0.06
    ctp
    0.06
    EIF
    0.06
    agine
    0.06
     Divider
    0.06
    Verifier
    0.06
    ilians
    0.06
    ecast
    0.06
    ITHER
    0.06
    stown
    0.06
    Activations Density 0.000%

    No Known Activations