© 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. 4-LLAMASCOPE-RES-32K
    11. 2744
    Prev
    Next
    INDEX
    Explanations

    variations of a specific word or term related to a subject, possibly indicating emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кÑĢа
    -0.16
    altet
    -0.15
    434
    -0.15
    arakter
    -0.15
    hardt
    -0.15
    å¦ĩ
    -0.15
    787
    -0.15
     Overlay
    -0.14
    а
    -0.14
    brid
    -0.14
    POSITIVE LOGITS
    enor
    0.17
    alles
    0.17
    en
    0.16
    μί
    0.15
    esy
    0.15
    dik
    0.15
     Cro
    0.15
    erro
    0.15
    æĶ
    0.15
    ikh
    0.14
    Activations Density 0.086%

    No Known Activations