© 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. 126203
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and educational institutions

    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
     resident
    -0.07
     Resident
    -0.06
     Patio
    -0.06
     some
    -0.06
     again
    -0.05
     what
    -0.05
     pro
    -0.05
    chor
    -0.05
    orch
    -0.05
     cole
    -0.05
    POSITIVE LOGITS
    #
    0.09
    @nate
    0.08
    /Branch
    0.08
    é§ħå¾ĴæŃ©
    0.08
    EGIN
    0.08
    ustil
    0.08
    rav
    0.08
     Branch
    0.08
    lâm
    0.08
    bruar
    0.08
    Activations Density 0.013%

    No Known Activations