© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125753
    Prev
    Next
    INDEX
    Explanations

    instances of the word "midway" and similar variations indicating a central point or transition

    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
     bo
    -0.06
    234
    -0.06
     Lomb
    -0.06
    mani
    -0.06
    ult
    -0.05
     s
    -0.05
     v
    -0.05
    -
    -0.05
    let
    -0.05
     plag
    -0.05
    POSITIVE LOGITS
    _ASSUME
    0.08
    .gdx
    0.08
     GenerationType
    0.08
    vtk
    0.08
    üf
    0.08
    ìľ¨
    0.08
    ringe
    0.08
    ,},↵
    0.08
    adro
    0.07
    ãĥ³ãĥĩ
    0.07
    Activations Density 0.000%

    No Known Activations