© 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. 3-LLAMASCOPE-RES-32K
    11. 454
    Prev
    Next
    INDEX
    Explanations

    methods with specific generic type parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ж
    -0.16
    жа
    -0.15
    agens
    -0.15
    ogne
    -0.14
    plat
    -0.14
    >((
    -0.14
    GRAM
    -0.14
    arend
    -0.14
    ailed
    -0.14
    seau
    -0.14
    POSITIVE LOGITS
    .gdx
    0.16
    lint
    0.15
    DDL
    0.14
    BaseContext
    0.14
    erty
    0.14
    ibur
    0.14
    untos
    0.14
    itter
    0.14
    ert
    0.14
     substantive
    0.14
    Activations Density 0.048%

    No Known Activations