© 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. 57749
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Angelina" or related references

    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
    .Selenium
    -0.10
    æľĭ
    -0.08
    eo
    -0.08
    iyah
    -0.08
    ceae
    -0.08
    yg
    -0.08
    annya
    -0.08
    urlencode
    -0.08
    oÅĪ
    -0.07
    skirts
    -0.07
    POSITIVE LOGITS
    ina
    0.08
    us
    0.07
    otti
    0.07
    rice
    0.07
    bote
    0.06
    orum
    0.06
     subt
    0.06
    ita
    0.06
    ical
    0.06
     trouble
    0.06
    Activations Density 0.006%

    No Known Activations