© 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. 17-LLAMASCOPE-RES-131K
    11. 82990
    Prev
    Next
    INDEX
    Explanations

    phrases indicating specific cases or examples

    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
    enan
    -0.07
    yz
    -0.07
    itters
    -0.06
    aÄį
    -0.06
    .serialization
    -0.06
    inz
    -0.06
    ragen
    -0.06
    ewe
    -0.06
    asi
    -0.06
    roach
    -0.06
    POSITIVE LOGITS
     case
    0.18
     cases
    0.16
     caso
    0.14
    case
    0.14
     Case
    0.13
    cases
    0.12
    _case
    0.12
     Cases
    0.12
    -case
    0.12
    Case
    0.11
    Activations Density 0.017%

    No Known Activations