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. 43575
    Prev
    Next
    INDEX
    Explanations

    phrases indicating rankings or positions within a hierarchy

    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
    Ïģια
    -0.06
    ------+------+
    -0.06
    below
    -0.06
    acin
    -0.06
     impressions
    -0.06
    avad
    -0.05
     impression
    -0.05
    kate
    -0.05
    urahan
    -0.05
     BELOW
    -0.05
    POSITIVE LOGITS
     summit
    0.14
     top
    0.13
     é¡
    0.12
     peak
    0.11
     tp
    0.10
    op
    0.10
    éłĤ
    0.10
    stop
    0.10
     summ
    0.10
     crown
    0.10
    Activations Density 0.024%

    No Known Activations