© 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. 3185
    Prev
    Next
    INDEX
    Explanations

    terms related to housing or residence

    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
    son
    -0.13
    ly
    -0.12
    ìĿĦ
    -0.12
    shape
    -0.11
    self
    -0.11
    sh
    -0.11
    shot
    -0.11
    rec
    -0.11
    name
    -0.10
    ting
    -0.10
    POSITIVE LOGITS
    es
    0.11
    esk
    0.09
    ously
    0.09
    able
    0.09
    ptron
    0.08
    y
    0.08
    ez
    0.08
    -minded
    0.08
    ourcem
    0.07
    au
    0.07
    Activations Density 0.075%

    No Known Activations