© 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. 15-LLAMASCOPE-RES-131K
    11. 103817
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or association

    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
    èĹ
    -0.08
    ereo
    -0.07
     SPORT
    -0.07
    andon
    -0.06
    IDL
    -0.06
    erez
    -0.06
    ainer
    -0.06
    ullen
    -0.06
    asing
    -0.06
    rench
    -0.06
    POSITIVE LOGITS
    otope
    0.07
     combination
    0.06
    ÃŃky
    0.06
    opper
    0.06
    anax
    0.06
    amba
    0.06
    IIIK
    0.06
     rig
    0.06
    akis
    0.06
    ky
    0.06
    Activations Density 0.021%

    No Known Activations