© 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. 75220
    Prev
    Next
    INDEX
    Explanations

    phrases indicating fundamental rights and societal health issues

    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
    iams
    -0.12
    tempts
    -0.12
    thern
    -0.11
    auty
    -0.11
    preter
    -0.10
    bidden
    -0.10
    gether
    -0.10
    gregate
    -0.10
    ystal
    -0.10
    itionally
    -0.09
    POSITIVE LOGITS
    ed
    0.10
    a
    0.09
    i
    0.07
    ãĥ¼ãģ®
    0.07
    ÛĮ
    0.06
    z
    0.06
    as
    0.06
    htags
    0.06
    omaly
    0.06
    isan
    0.06
    Activations Density 0.376%

    No Known Activations