© 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. 16-LLAMASCOPE-RES-32K
    11. 1486
    Prev
    Next
    INDEX
    Explanations

    phrases related to substitutions or replacements 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 @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morton
    -0.17
    aso
    -0.15
    utin
    -0.14
    urse
    -0.14
    atee
    -0.14
    allas
    -0.14
    ÑĤик
    -0.14
     Denis
    -0.14
    bonus
    -0.14
    warts
    -0.14
    POSITIVE LOGITS
     replace
    0.37
     replacing
    0.35
     replaced
    0.34
     Replace
    0.34
     replacement
    0.32
     replaces
    0.31
    replace
    0.31
     Replacement
    0.30
    Replace
    0.30
    _replace
    0.29
    Activations Density 0.139%

    No Known Activations