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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95924
    Prev
    Next
    INDEX
    Explanations

    phrases related to availability and conditions for obtaining or using something

    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
    aul
    -0.09
    ROUT
    -0.07
    uly
    -0.07
    il
    -0.07
    ÅĪ
    -0.06
    lds
    -0.06
     çĥ
    -0.06
    uar
    -0.06
    raid
    -0.06
     dân
    -0.06
    POSITIVE LOGITS
    idor
    0.07
    worthy
    0.07
    andest
    0.06
    _foreign
    0.06
    ialog
    0.06
    AGO
    0.06
     Hayden
    0.06
    sten
    0.06
    oden
    0.06
     Bas
    0.06
    Activations Density 0.144%

    No Known Activations