© 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. 5-LLAMASCOPE-RES-131K
    6. 126079
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hired" and its variations in different contexts

    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
    otch
    -0.08
    atte
    -0.06
    cket
    -0.06
    oyer
    -0.06
    rouw
    -0.06
    urre
    -0.06
    avr
    -0.06
    .azure
    -0.06
    appable
    -0.06
    aries
    -0.06
    POSITIVE LOGITS
     Lor
    0.07
    eus
    0.07
    ñana
    0.07
    /lic
    0.06
    odus
    0.06
    .toolbox
    0.06
    .opensource
    0.06
    ázd
    0.06
    eous
    0.06
    Äįku
    0.06
    Activations Density 0.005%

    No Known Activations