© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 58476
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "house" in various 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
    zym
    -0.08
    rå
    -0.08
    ëĭ¤
    -0.08
    ãģĬãĤĬ
    -0.08
    thal
    -0.08
    amente
    -0.08
    owa
    -0.07
    thic
    -0.07
    ERA
    -0.07
    ist
    -0.07
    POSITIVE LOGITS
    guest
    0.12
    keeping
    0.12
    wives
    0.11
    wife
    0.10
    wares
    0.10
    clean
    0.10
    mates
    0.10
    plants
    0.09
    (es
    0.09
    elijke
    0.09
    Activations Density 0.036%

    No Known Activations