© 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. 76897
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic interactions and issues

    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
    @a
    -0.07
     nond
    -0.06
    jian
    -0.06
     hÃłnh
    -0.06
    ãĥĨãĥ«
    -0.06
    anche
    -0.06
    à¤Ĥर
    -0.06
     conexao
    -0.06
    ikat
    -0.06
     Sonra
    -0.05
    POSITIVE LOGITS
    Å¡et
    0.09
    }elseif
    0.07
    é¡ĺ
    0.07
    Sector
    0.07
    /static
    0.07
    ooks
    0.06
    ìĿ´ìĹIJ
    0.06
    _sector
    0.06
    foon
    0.06
     sector
    0.06
    Activations Density 0.001%

    No Known Activations