© 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. 7614
    Prev
    Next
    INDEX
    Explanations

    reviews that express opinions about the quality and enjoyment of films

    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
    лиÑĤ
    -0.15
    åĢĴ
    -0.14
     Useful
    -0.14
    aoke
    -0.14
    çª
    -0.13
    used
    -0.13
    æľ«
    -0.13
    ropp
    -0.13
    igenous
    -0.13
    alat
    -0.13
    POSITIVE LOGITS
     entertaining
    0.19
     paced
    0.18
     enjoyable
    0.17
    elper
    0.17
    amb
    0.16
     entertain
    0.16
     leagues
    0.16
     ambitious
    0.15
     darker
    0.15
    .watch
    0.15
    Activations Density 0.157%

    No Known Activations