© 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. 87143
    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
     teg
    -0.06
    itm
    -0.06
    oren
    -0.06
     Matth
    -0.06
     ere
    -0.06
     /
    -0.06
    666
    -0.06
    buah
    -0.05
    isser
    -0.05
     Hao
    -0.05
    POSITIVE LOGITS
    vature
    0.07
    fé
    0.07
    å°¼äºļ
    0.07
    vig
    0.07
     esac
    0.07
    anship
    0.07
     rám
    0.06
    ůst
    0.06
    祥
    0.06
    tainment
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.