© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129056
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or relationships

    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
    ous
    -0.07
    ala
    -0.06
    atta
    -0.06
    gh
    -0.06
    Ä
    -0.06
    acid
    -0.05
    alist
    -0.05
    untime
    -0.05
    oon
    -0.05
     gun
    -0.05
    POSITIVE LOGITS
     Riley
    0.07
    ropolis
    0.07
     lived
    0.07
    edback
    0.07
     Annunci
    0.07
    385
    0.07
    æ®ĸ
    0.07
    ãĤ´ãĥª
    0.07
    Incre
    0.06
    addir
    0.06
    Activations Density 0.010%

    No Known Activations