© 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. 82538
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ola
    -0.06
     provisional
    -0.06
    877
    -0.06
     Abilities
    -0.06
     Provision
    -0.05
     lamp
    -0.05
    ************************************************************************
    -0.05
     standart
    -0.05
     succesfully
    -0.05
    hes
    -0.05
    POSITIVE LOGITS
    ayıp
    0.07
    ahy
    0.07
    osl
    0.07
    fé
    0.07
    mana
    0.07
    ersist
    0.06
    podob
    0.06
    ÅĤaw
    0.06
    etten
    0.06
    utan
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.