© 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. 23-LLAMASCOPE-RES-32K
    11. 20826
    Prev
    Next
    INDEX
    Explanations

    inquiries and discussions related to questions, answers, and knowledge evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iqueta
    -0.15
    quan
    -0.14
    .dense
    -0.14
    orget
    -0.13
    irket
    -0.13
    aign
    -0.13
    ̧
    -0.13
    ensch
    -0.13
    dig
    -0.13
    uled
    -0.13
    POSITIVE LOGITS
     answer
    1.30
     answers
    1.24
     answered
    1.11
     Answer
    1.09
    answer
    1.06
     Answers
    0.98
    çŃĶæ¡Ī
    0.97
     ANSW
    0.96
    Answer
    0.95
     answering
    0.95
    Activations Density 0.527%

    No Known Activations