© 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. 17-LLAMASCOPE-RES-131K
    11. 16074
    Prev
    Next
    INDEX
    Explanations

    assertions related to comparisons in programming or testing contexts

    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
    ala
    -0.07
    ini
    -0.07
     behalf
    -0.06
    elves
    -0.06
    eti
    -0.06
    .i
    -0.06
    eme
    -0.06
    erson
    -0.06
    i
    -0.06
     like
    -0.06
    POSITIVE LOGITS
    gnore
    0.09
    AndHashCode
    0.08
     sophistic
    0.08
    vanced
    0.08
     Soph
    0.07
    ç¾
    0.07
    antor
    0.07
    ì°¬
    0.07
    егоÑĢ
    0.07
    bÃŃ
    0.07
    Activations Density 0.004%

    No Known Activations