© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96995
    Prev
    Next
    INDEX
    Explanations

    references to the concept of returning or coming back

    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
    vore
    -0.07
    Ø·ÙĦ
    -0.07
    onus
    -0.07
    fen
    -0.07
    è£ģ
    -0.07
    aukee
    -0.07
    _tokenize
    -0.07
    lems
    -0.07
    oni
    -0.07
    -opacity
    -0.07
    POSITIVE LOGITS
     to
    0.07
     later
    0.07
     Ellison
    0.06
     Naz
    0.06
     exact
    0.06
    913
    0.06
     Davis
    0.06
     hourly
    0.05
    @Id
    0.05
    608
    0.05
    Activations Density 0.021%

    No Known Activations