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. 44144
    Prev
    Next
    INDEX
    Explanations

    references to future time

    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
    asers
    -0.08
    ses
    -0.07
    RenderTarget
    -0.07
    tü
    -0.07
    abwe
    -0.06
    sj
    -0.06
    sparse
    -0.06
    λοÏĤ
    -0.06
    ritos
    -0.06
    sb
    -0.06
    POSITIVE LOGITS
    ally
    0.20
    -on
    0.14
    ALLY
    0.14
    ality
    0.13
    -than
    0.13
    -stage
    0.13
     than
    0.12
     down
    0.12
     stages
    0.12
    on
    0.11
    Activations Density 0.024%

    No Known Activations