© 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. 21345
    Prev
    Next
    INDEX
    Explanations

    references to grammatical structures and language learning concepts

    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
     slang
    -0.15
    umd
    -0.15
    lint
    -0.15
    å¹ķ
    -0.15
     synonym
    -0.14
    ocabulary
    -0.14
     bul
    -0.14
    ewire
    -0.14
    (||
    -0.14
    ndl
    -0.14
    POSITIVE LOGITS
     accus
    0.21
     morph
    0.20
     morphology
    0.20
     declined
    0.20
     inf
    0.20
     endings
    0.20
     Morph
    0.19
     decl
    0.19
     agreement
    0.18
     Case
    0.18
    Activations Density 0.024%

    No Known Activations