© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 76558
    Prev
    Next
    INDEX
    Explanations

    references to claims and assertions made in media and public statements

    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
    vrier
    -0.06
     ë´ī
    -0.06
    ACKET
    -0.06
    lagen
    -0.06
     anonymity
    -0.06
    éģĬ
    -0.06
    llum
    -0.06
     philosoph
    -0.06
    706
    -0.06
     constitution
    -0.06
    POSITIVE LOGITS
     claim
    0.11
     CLAIM
    0.10
     claims
    0.10
    claims
    0.10
    Claims
    0.10
    claim
    0.09
     Claims
    0.09
     Claim
    0.09
    CLAIM
    0.09
    Claim
    0.09
    Activations Density 0.022%

    No Known Activations