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. 43429
    Prev
    Next
    INDEX
    Explanations

    phrases related to choices or alternatives

    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
    Optional
    -0.09
    аниÑĨ
    -0.09
    optional
    -0.08
    _optional
    -0.08
     Optional
    -0.07
    Options
    -0.07
    _OPTIONS
    -0.07
     optional
    -0.07
    s
    -0.07
    OperationException
    -0.07
    POSITIVE LOGITS
    ality
    0.19
    als
    0.13
    ally
    0.13
     available
    0.12
    nal
    0.12
    nelle
    0.10
    nement
    0.10
    nel
    0.10
    ALS
    0.10
    available
    0.09
    Activations Density 0.029%

    No Known Activations