© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 93988
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating sequential or conditional relationships

    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
    ce
    -0.07
    опол
    -0.07
    ugg
    -0.07
    orce
    -0.07
    740
    -0.06
     Tang
    -0.06
    andy
    -0.06
    care
    -0.06
    ipl
    -0.06
     Advertisement
    -0.06
    POSITIVE LOGITS
    žel
    0.08
    rix
    0.07
    istrovstvÃŃ
    0.07
     zwar
    0.07
     bla
    0.06
     ìĭ¶
    0.06
     ê°ĻìĿĢ
    0.06
     foes
    0.06
    ftype
    0.06
    ENN
    0.06
    Activations Density 0.031%

    No Known Activations