© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 3126
    Prev
    Next
    INDEX
    Explanations

    instances of quantity or counting expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ıl
    -0.14
    oute
    -0.14
    etta
    -0.14
    okol
    -0.14
    agen
    -0.14
    ILLISE
    -0.14
     esl
    -0.13
    oogle
    -0.13
    oke
    -0.13
     Guess
    -0.13
    POSITIVE LOGITS
    adox
    0.14
    ITERAL
    0.14
    ãĥªãĥ¼ãĤº
    0.14
    afa
    0.13
     Abrams
    0.13
    ernaut
    0.13
    uentes
    0.13
    imson
    0.13
    enin
    0.13
    _allowed
    0.13
    Activations Density 0.044%

    No Known Activations