© 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. 57586
    Prev
    Next
    INDEX
    Explanations

    references to online interactions and communication, particularly in relation to social media and email

    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
     Hen
    -0.06
    chner
    -0.06
    /effects
    -0.06
     forces
    -0.06
     Lap
    -0.06
     bon
    -0.06
    criptor
    -0.06
     free
    -0.06
    upp
    -0.06
    pmat
    -0.05
    POSITIVE LOGITS
    //{{
    0.09
     samot
    0.08
     Ñģамой
    0.07
     INLINE
    0.07
     contexto
    0.07
     CONTEXT
    0.07
    Collapsed
    0.07
    instanc
    0.07
    longleftrightarrow
    0.07
    TEGR
    0.07
    Activations Density 0.010%

    No Known Activations