© 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. 78685
    Prev
    Next
    INDEX
    Explanations

    instances of the word "follow" and its variations associated with social media engagement

    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
    egov
    -0.07
    lical
    -0.07
    iosa
    -0.07
     Imp
    -0.07
    lund
    -0.07
     Entr
    -0.06
    eness
    -0.06
    èĮĤ
    -0.06
    onom
    -0.06
    lara
    -0.06
    POSITIVE LOGITS
    ings
    0.08
    ÂŃing
    0.08
    inh
    0.07
    isay
    0.07
    ed
    0.07
    -follow
    0.07
    zi
    0.07
    cker
    0.07
    able
    0.07
     Us
    0.07
    Activations Density 0.004%

    No Known Activations