© 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. 15-LLAMASCOPE-RES-131K
    11. 1280
    Prev
    Next
    INDEX
    Explanations

    phrases indicating partiality or incompleteness

    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
    ure
    -0.06
     charges
    -0.06
     but
    -0.06
     inc
    -0.06
    ack
    -0.06
    elle
    -0.06
    ach
    -0.06
    ader
    -0.06
    992
    -0.05
     protected
    -0.05
    POSITIVE LOGITS
     parte
    0.09
     part
    0.09
    ROSS
    0.09
    éĥ¨åĪĨ
    0.08
     ÑĩаÑģÑĤÑĮ
    0.08
     partie
    0.08
    \/\/
    0.08
     ÑĩаÑģÑĤина
    0.08
    .dsl
    0.08
    eyse
    0.08
    Activations Density 0.018%

    No Known Activations