Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128946
    Prev
    Next
    INDEX
    Explanations

    mentions of "Capricorn"

    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
    iker
    -0.07
    kers
    -0.07
    á»ģn
    -0.07
    èĨľ
    -0.07
    kowski
    -0.07
    اØŃØ©
    -0.07
    eniable
    -0.07
    awan
    -0.07
    ikers
    -0.07
    berman
    -0.06
    POSITIVE LOGITS
    isd
    0.07
    reno
    0.06
     Aqu
    0.06
     Placement
    0.06
     slo
    0.06
    328
    0.06
     steel
    0.06
     Decompiled
    0.06
    aille
    0.06
    _FMT
    0.06
    Activations Density 0.001%

    No Known Activations