© 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. 29-LLAMASCOPE-RES-32K
    11. 13581
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "ex-" indicating actions or processes of removal or reconsideration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĤ
    -0.16
    á»ģn
    -0.15
    nez
    -0.15
    缣
    -0.15
    IPLE
    -0.15
    latex
    -0.14
    ocate
    -0.14
     pip
    -0.14
    vero
    -0.14
    iveau
    -0.14
    POSITIVE LOGITS
    amination
    0.26
    amin
    0.25
    periments
    0.25
    hib
    0.24
    hibition
    0.23
    agger
    0.23
    aminer
    0.23
    change
    0.23
    amine
    0.23
    ercise
    0.22
    Activations Density 0.019%

    No Known Activations