© 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. 40739
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions with media or online navigation elements

    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
    595
    -0.07
    azy
    -0.06
     zav
    -0.06
     rare
    -0.06
     run
    -0.06
    abase
    -0.06
    idae
    -0.06
    urse
    -0.06
     Succ
    -0.06
     Kas
    -0.06
    POSITIVE LOGITS
    ÑĢаÐ
    0.07
    otionEvent
    0.07
    eÅŁit
    0.07
    ãĥĥãĥĪ
    0.07
    OVE
    0.07
    /vnd
    0.07
    robat
    0.06
    }elseif
    0.06
    Tpl
    0.06
    .tpl
    0.06
    Activations Density 0.002%

    No Known Activations