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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84365
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate possession or the act of having 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
    yle
    -0.07
    onn
    -0.07
     Cout
    -0.06
    anning
    -0.06
    AMS
    -0.06
    veloper
    -0.06
     çħ
    -0.06
     Weaver
    -0.06
    deaux
    -0.06
    ams
    -0.06
    POSITIVE LOGITS
    emplate
    0.06
     Trouble
    0.06
    ãĥ«ãĥĪ
    0.06
    .fm
    0.06
    aland
    0.06
    REDIENT
    0.06
     trouble
    0.06
    alia
    0.06
    ãģ¹ãģį
    0.06
    åħ±
    0.06
    Activations Density 0.011%

    No Known Activations