© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 10-LLAMASCOPE-RES-32K
    11. 23520
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "on" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oretical
    -0.15
    owl
    -0.15
    quarters
    -0.15
    ily
    -0.15
    iring
    -0.15
    ened
    -0.14
    762
    -0.14
    ties
    -0.13
    ringe
    -0.13
    pawn
    -0.13
    POSITIVE LOGITS
     behalf
    0.37
    /off
    0.29
    shore
    0.24
    -site
    0.22
    etime
    0.21
    -the
    0.20
    /about
    0.19
    -demand
    0.19
    -board
    0.18
    look
    0.18
    Activations Density 0.523%

    No Known Activations