© 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. 12003
    Prev
    Next
    INDEX
    Explanations

    expressions of spiritual encouragement and the importance of faith

    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
     Becker
    -0.17
    jes
    -0.17
    ico
    -0.16
    anje
    -0.15
    LC
    -0.15
     cate
    -0.15
     Lens
    -0.14
     Hass
    -0.14
    ique
    -0.14
    chen
    -0.14
    POSITIVE LOGITS
     travail
    0.16
    gebn
    0.15
    prak
    0.15
     proph
    0.15
    shift
    0.15
    chop
    0.15
    ÃŃnh
    0.15
    lish
    0.15
     destin
    0.15
    ä¹ĥ
    0.15
    Activations Density 0.034%

    No Known Activations