© 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. 29511
    Prev
    Next
    INDEX
    Explanations

    terms related to terrorism and insurgency

    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
    ãģ«è¡Į
    -0.06
     pulp
    -0.06
    elsey
    -0.06
    erve
    -0.06
    689
    -0.06
    ject
    -0.06
    stamp
    -0.06
    ower
    -0.06
    รà¸Ķ
    -0.06
    /me
    -0.06
    POSITIVE LOGITS
     leader
    0.07
    -toggler
    0.07
    /ext
    0.07
    Äĥn
    0.07
    roadcast
    0.07
    rawn
    0.07
    /problem
    0.07
    ½Ķ
    0.07
    aeda
    0.07
     Leader
    0.06
    Activations Density 0.020%

    No Known Activations