© 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. 126809
    Prev
    Next
    INDEX
    Explanations

    place names, particularly related to geographic locations

    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
    adol
    -0.07
    éĢŁ
    -0.07
    bable
    -0.06
    zag
    -0.06
    fault
    -0.06
    è¬Ŀ
    -0.06
    oho
    -0.06
    lings
    -0.06
    WSC
    -0.06
    tres
    -0.06
    POSITIVE LOGITS
    shire
    0.08
    çĭ
    0.07
    agues
    0.07
     Braun
    0.07
    amel
    0.07
    amas
    0.07
    urm
    0.07
    oulos
    0.07
    stown
    0.06
    perl
    0.06
    Activations Density 0.002%

    No Known Activations