© 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. 9-LLAMASCOPE-RES-131K
    11. 95555
    Prev
    Next
    INDEX
    Explanations

    keywords associated with certifications and security credentials in technology 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
    tape
    -0.07
    brig
    -0.06
     Tape
    -0.06
    nw
    -0.06
    teenth
    -0.06
    onian
    -0.06
    quarter
    -0.06
    /select
    -0.06
    cret
    -0.05
    na
    -0.05
    POSITIVE LOGITS
     pari
    0.07
    strcasecmp
    0.07
    çĮ
    0.07
    weather
    0.07
     weather
    0.07
     Weather
    0.07
    DAQ
    0.07
    æ³¥
    0.07
    ynchronously
    0.07
    owied
    0.07
    Activations Density 0.001%

    No Known Activations