© 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. 27-LLAMASCOPE-RES-32K
    11. 2061
    Prev
    Next
    INDEX
    Explanations

    elements of theatrical drama and narrative structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     movies
    -0.18
     filmes
    -0.16
     films
    -0.15
     documentaries
    -0.15
     gratuitement
    -0.15
     Filme
    -0.15
     Cannes
    -0.15
    .tc
    -0.15
     cine
    -0.14
    ICAST
    -0.14
    POSITIVE LOGITS
     onstage
    0.23
     Act
    0.20
     sol
    0.18
     stage
    0.18
     audience
    0.17
     du
    0.17
     doubling
    0.17
    ENO
    0.17
    odos
    0.17
     entrances
    0.16
    Activations Density 0.018%

    No Known Activations