© 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. 15-LLAMASCOPE-RES-32K
    11. 23439
    Prev
    Next
    INDEX
    Explanations

    assertions and affirmations of knowledge or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VERY
    -0.14
    á»ĩu
    -0.14
     cÃłng
    -0.14
     informal
    -0.13
    umper
    -0.13
    ieux
    -0.13
     gore
    -0.13
     cue
    -0.13
    ington
    -0.13
    VERY
    -0.13
    POSITIVE LOGITS
     actual
    0.32
     actually
    0.29
    actual
    0.27
    羣æŃ£
    0.26
     Actual
    0.24
     unlike
    0.24
    Actual
    0.22
     instead
    0.21
    (actual
    0.21
    actually
    0.21
    Activations Density 0.445%

    No Known Activations