© 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. 119375
    Prev
    Next
    INDEX
    Explanations

    terms related to effective communication and clarity in conveying 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
    ĥĿ
    -0.08
    ead
    -0.07
    éĺµ
    -0.07
    IVAL
    -0.07
    urre
    -0.07
    ovaly
    -0.07
    ervo
    -0.06
    SWG
    -0.06
    UNET
    -0.06
    kj
    -0.06
    POSITIVE LOGITS
     clr
    0.07
    æłª
    0.07
     crystal
    0.06
     lightning
    0.06
     Crystal
    0.06
     hav
    0.06
     Kan
    0.06
     conversation
    0.06
     responsibility
    0.06
    logradouro
    0.06
    Activations Density 0.001%

    No Known Activations