© 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. 17709
    Prev
    Next
    INDEX
    Explanations

    instances of the character or word "a"

    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
    842
    -0.06
    uffix
    -0.06
    ayet
    -0.06
    ладÑĥ
    -0.06
    bere
    -0.06
     Hoch
    -0.05
    NSS
    -0.05
    ebi
    -0.05
    ÙĦاØŃ
    -0.05
    ertz
    -0.05
    POSITIVE LOGITS
    isel
    0.07
    appa
    0.07
    yon
    0.07
    纸
    0.07
    ounter
    0.07
    usta
    0.07
    immer
    0.06
     INTERFACE
    0.06
    تاب
    0.06
    Ïĩι
    0.06
    Activations Density 0.000%

    No Known Activations