© 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. 87732
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing various quantities or characteristics

    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
    olumn
    -0.08
    isposable
    -0.08
    ìĤ´
    -0.07
    esktop
    -0.07
    _FP
    -0.07
    clk
    -0.07
    AreaView
    -0.07
    _TypeDef
    -0.07
     éĸ¢éĢ£
    -0.07
    fic
    -0.07
    POSITIVE LOGITS
     legacy
    0.07
    款
    0.07
     Legacy
    0.06
     fellow
    0.06
    okane
    0.06
    gio
    0.06
     junge
    0.06
     Connection
    0.06
     Friedrich
    0.06
    ousand
    0.05
    Activations Density 0.031%

    No Known Activations