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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 2770
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss evaluations or critiques of films

    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
    antor
    -0.08
    ONA
    -0.08
    asso
    -0.08
     Kend
    -0.07
    plete
    -0.07
    latest
    -0.07
     latest
    -0.07
    .getOrElse
    -0.06
    anter
    -0.06
    LETE
    -0.06
    POSITIVE LOGITS
     overall
    0.09
     speaking
    0.08
    Speaking
    0.07
     Overall
    0.07
    Overall
    0.07
     Speaking
    0.07
    -speaking
    0.07
    overall
    0.07
     spoken
    0.06
    spe
    0.06
    Activations Density 0.006%

    No Known Activations