© 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. 72150
    Prev
    Next
    INDEX
    Explanations

    nouns that refer to physical locations and entities, particularly in various social contexts

    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
    efa
    -0.07
    ?url
    -0.07
    ä½įäºİ
    -0.07
    опÑĢи
    -0.07
    stride
    -0.07
    .sax
    -0.06
     Decompiled
    -0.06
    tach
    -0.06
    ä½įæĸ¼
    -0.06
    engl
    -0.06
    POSITIVE LOGITS
    apore
    0.07
    olars
    0.06
    igo
    0.06
    اتÛĮ
    0.06
    ohana
    0.06
    _mA
    0.06
    äre
    0.06
    apol
    0.05
     Kin
    0.05
    820
    0.05
    Activations Density 0.052%

    No Known Activations