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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118490
    Prev
    Next
    INDEX
    Explanations

    the word "All" or its variations in different 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
    å¤ķ
    -0.06
     ÙĪاØŃدة
    -0.06
    obsolete
    -0.06
    avl
    -0.06
     Ritch
    -0.06
     valign
    -0.06
    맹
    -0.05
     BATCH
    -0.05
     Lancaster
    -0.05
     Bert
    -0.05
    POSITIVE LOGITS
    aise
    0.07
    алÑĸз
    0.07
    ija
    0.07
    xon
    0.07
     Geo
    0.07
    aggi
    0.06
    orge
    0.06
     ÑĩиÑģ
    0.06
    ActionCreators
    0.06
    Geo
    0.06
    Activations Density 0.000%

    No Known Activations