© 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. 26-LLAMASCOPE-RES-32K
    11. 21937
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate various types of actions or responses related to lists or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mostly
    -0.19
     вÑģеÑħ
    -0.19
     generally
    -0.18
    éĢļ常
    -0.18
    ä½ķãģĭ
    -0.18
    mostly
    -0.18
     always
    -0.17
     vÄĽtÅ¡inou
    -0.17
     largely
    -0.17
     Mostly
    -0.17
    POSITIVE LOGITS
     even
    0.40
     simply
    0.35
    even
    0.34
     sogar
    0.34
     outright
    0.32
    çĶļèĩ³
    0.32
     downright
    0.31
     dokonce
    0.29
     Even
    0.27
    Even
    0.27
    Activations Density 0.490%

    No Known Activations