© 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. 24-LLAMASCOPE-RES-32K
    11. 20708
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 'D' in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocking
    -0.19
    avis
    -0.18
    addy
    -0.18
    elay
    -0.17
    ummy
    -0.17
    etermin
    -0.17
    oes
    -0.16
    emand
    -0.16
    airy
    -0.16
    rug
    -0.16
    POSITIVE LOGITS
    alm
    0.19
    zer
    0.18
    ighton
    0.16
    jer
    0.15
    ahoo
    0.14
    alk
    0.14
    endale
    0.14
    ido
    0.14
    elf
    0.14
    end
    0.14
    Activations Density 0.047%

    No Known Activations