Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 20487
    Prev
    Next
    INDEX
    Explanations

    references to specific movies and their themes, plot points, or characteristics

    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
     Burb
    -0.15
    åĪĬ
    -0.15
    ượng
    -0.14
    ancement
    -0.14
    inas
    -0.14
    445
    -0.14
     Xt
    -0.14
    tra
    -0.14
     Verse
    -0.14
    enge
    -0.14
    POSITIVE LOGITS
     Raiders
    0.20
     Citizen
    0.18
     Forrest
    0.17
     Breakfast
    0.17
     classics
    0.16
     Taxi
    0.16
     Saving
    0.16
     Gladiator
    0.15
     Cas
    0.15
     Gone
    0.15
    Activations Density 0.209%

    No Known Activations