© 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. 125460
    Prev
    Next
    INDEX
    Explanations

    guidance related to job applications and legal advice

    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
    ims
    -0.08
    &w
    -0.07
    InSection
    -0.06
    izar
    -0.06
    inis
    -0.06
     perms
    -0.06
    uisse
    -0.06
    ammen
    -0.06
    aaS
    -0.06
    ONTAL
    -0.06
    POSITIVE LOGITS
    anlı
    0.06
    WARDED
    0.06
    oment
    0.06
    fang
    0.06
    çĥĪ
    0.06
     Stateless
    0.06
    outers
    0.06
    itel
    0.06
     hyp
    0.06
    ÂŃtion
    0.06
    Activations Density 0.003%

    No Known Activations