© 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. 5-LLAMASCOPE-RES-131K
    11. 126566
    Prev
    Next
    INDEX
    Explanations

    email addresses or contact information

    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
    assa
    -0.07
     Sas
    -0.06
    vine
    -0.06
    iese
    -0.06
    aro
    -0.06
    alles
    -0.06
    sdale
    -0.06
    onder
    -0.06
    runner
    -0.06
    ivate
    -0.06
    POSITIVE LOGITS
    éł
    0.08
    egend
    0.07
    umper
    0.07
    Ú¯ÛĮرÛĮ
    0.06
    ucha
    0.06
     edi
    0.06
    regnum
    0.06
     aforementioned
    0.06
    ALLY
    0.06
    Accessor
    0.06
    Activations Density 0.006%

    No Known Activations