© 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. 17-LLAMASCOPE-RES-131K
    11. 129166
    Prev
    Next
    INDEX
    Explanations

    phrases related to partnership and collaboration

    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
    _DU
    -0.07
    Ñģол
    -0.07
     dyst
    -0.07
    çĹ
    -0.07
     bullet
    -0.07
    اطر
    -0.07
    .Generated
    -0.06
     Kitty
    -0.06
    teg
    -0.06
    eos
    -0.06
    POSITIVE LOGITS
    ril
    0.07
     crime
    0.07
     Crime
    0.07
    jak
    0.06
    ichel
    0.06
    ASN
    0.06
    ฯ
    0.06
    illo
    0.06
     mutually
    0.06
     pil
    0.05
    Activations Density 0.012%

    No Known Activations