© 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. 20-LLAMASCOPE-RES-32K
    11. 13116
    Prev
    Next
    INDEX
    Explanations

    ambiguous statements regarding certainty and knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    524
    -0.15
    267
    -0.15
    rzy
    -0.14
    ourd
    -0.14
    ItemAt
    -0.14
    ibold
    -0.14
    анÑĥ
    -0.14
    urdy
    -0.13
    Ìī
    -0.13
    isto
    -0.13
    POSITIVE LOGITS
     unknown
    0.75
    unknown
    0.67
     Unknown
    0.63
    Unknown
    0.60
     unclear
    0.56
    ä¸įçŁ¥éģĵ
    0.55
     UNKNOWN
    0.54
    _unknown
    0.52
     unsure
    0.49
    UNKNOWN
    0.49
    Activations Density 0.428%

    No Known Activations