© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 986
    Prev
    Next
    INDEX
    Explanations

    references to children and familial relationships

    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
    LOSS
    -0.07
    cone
    -0.06
    ASF
    -0.06
    ÑĤоÑĦ
    -0.06
     سپ
    -0.06
    opers
    -0.06
    arshal
    -0.06
    ochastic
    -0.06
    /count
    -0.06
    anggal
    -0.06
    POSITIVE LOGITS
    VC
    0.08
    hores
    0.07
    Inflater
    0.06
    ÙĬاÙĨ
    0.06
    igram
    0.06
    essler
    0.06
    ipse
    0.06
    iat
    0.06
    bk
    0.06
    oods
    0.06
    Activations Density 0.016%

    No Known Activations