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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5311
    Prev
    Next
    INDEX
    Explanations

    words related to "man" or "human-like" references

    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
    OCKET
    -0.08
    regnum
    -0.07
    OKIE
    -0.07
    lament
    -0.06
    compat
    -0.06
    APA
    -0.06
    аниÑĨ
    -0.06
    è©
    -0.06
    è¥
    -0.06
    ÑĢоÑĤ
    -0.06
    POSITIVE LOGITS
    ecer
    0.09
    tha
    0.07
    ullah
    0.07
    uele
    0.07
    uzzi
    0.07
    irim
    0.07
    ishi
    0.07
    odd
    0.07
    koli
    0.07
    ripp
    0.07
    Activations Density 0.003%

    No Known Activations