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. 44184
    Prev
    Next
    INDEX
    Explanations

    terms related to resonance and scattering in nuclear physics

    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
    .scalablytyped
    -0.07
    dfs
    -0.06
    KeyCode
    -0.06
     rock
    -0.06
    endif
    -0.06
     Hend
    -0.06
    ABCDEFG
    -0.06
     Billy
    -0.06
     Betty
    -0.06
    imation
    -0.05
    POSITIVE LOGITS
    ant
    0.12
    antly
    0.11
    ators
    0.10
    ances
    0.10
    ator
    0.09
    antor
    0.08
    antt
    0.08
    ANCES
    0.08
     antenn
    0.08
     denominator
    0.08
    Activations Density 0.009%

    No Known Activations