Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87375
    Prev
    Next
    INDEX
    Explanations

    complex emotional dynamics and conflicts within interpersonal relationships

    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
    ellas
    -0.07
    linger
    -0.07
    ingers
    -0.07
    lement
    -0.07
    ontent
    -0.07
    ActionCreators
    -0.07
    ãĥĭãĥ¼
    -0.07
    annis
    -0.07
    ictim
    -0.07
    enen
    -0.07
    POSITIVE LOGITS
    inst
    0.06
    \:
    0.06
    anzeigen
    0.06
    æĬ
    0.06
    iless
    0.06
     lÃłm
    0.06
    ÑĢÑĸз
    0.06
    opis
    0.06
     Ekon
    0.06
     Snowden
    0.05
    Activations Density 0.047%

    No Known Activations