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

    Neuronpedia

    Jacobian LensNEW
    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. 23-LLAMASCOPE-RES-32K
    11. 2669
    Prev
    Next
    INDEX
    Explanations

    concepts related to individual health risks and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arya
    -0.14
    opsis
    -0.13
    aval
    -0.13
    eler
    -0.13
    ovich
    -0.13
     doubly
    -0.13
    oplay
    -0.12
    pek
    -0.12
    awah
    -0.12
    ÙĨÙĩ
    -0.12
    POSITIVE LOGITS
     individual
    1.27
     Individual
    1.07
    individual
    1.06
    Individual
    0.97
    _individual
    0.84
     individ
    0.81
     individually
    0.69
     einzel
    0.68
    个
    0.68
    åĢĭ
    0.63
    Activations Density 0.621%

    No Known Activations