Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43995
    Prev
    Next
    INDEX
    Explanations

    references to the Metro area and its related entities or characteristics

    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
    yr
    -0.08
    y
    -0.08
    yre
    -0.08
    yb
    -0.07
    ieg
    -0.07
    rlen
    -0.07
    yne
    -0.07
    rng
    -0.07
    669
    -0.06
    arov
    -0.06
    POSITIVE LOGITS
    plit
    0.14
    logy
    0.14
    plex
    0.14
    PCS
    0.14
    logical
    0.12
    sexual
    0.12
    bus
    0.10
     Manila
    0.10
    hm
    0.10
     pcs
    0.09
    Activations Density 0.007%

    No Known Activations