© 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. 24-LLAMASCOPE-RES-32K
    11. 18882
    Prev
    Next
    INDEX
    Explanations

    phrases related to amateur golf tournaments and their prize regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VE
    -0.14
    uras
    -0.14
     Glob
    -0.14
     Immutable
    -0.14
    okedex
    -0.14
    åĬŀ
    -0.13
    utz
    -0.13
     fan
    -0.13
     masking
    -0.13
    kit
    -0.13
    POSITIVE LOGITS
     handicap
    0.19
     Stable
    0.18
     gross
    0.17
     scramble
    0.17
    /cart
    0.16
     Hole
    0.16
     greens
    0.16
    stable
    0.15
    باØŃ
    0.15
     outing
    0.15
    Activations Density 0.051%

    No Known Activations