© 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 EvalsExportsinterp-engineNEWAPI 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. 105439
    Prev
    Next
    INDEX
    Explanations

    statements regarding the credibility and verification of information

    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
    rosso
    -0.06
    uel
    -0.06
     mobility
    -0.05
     scor
    -0.05
     propos
    -0.05
    TH
    -0.05
    513
    -0.05
    Hint
    -0.05
    agne
    -0.05
     hypoc
    -0.05
    POSITIVE LOGITS
     reporting
    0.08
    tring
    0.08
    DCF
    0.08
    juan
    0.08
    PTY
    0.08
    VML
    0.08
    ãĥĵãĥ¼
    0.08
     Reporting
    0.08
    å§ij
    0.08
     CONTEXT
    0.07
    Activations Density 0.039%

    No Known Activations