© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    references to "next generation" and its variations in various contexts

    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
    lian
    -0.16
    ëł´
    -0.16
    lator
    -0.15
    late
    -0.14
     Typ
    -0.14
    byss
    -0.14
    inge
    -0.14
    uzey
    -0.13
    _RC
    -0.13
    \Schema
    -0.13
    POSITIVE LOGITS
    hr
    0.16
    clusive
    0.16
    clus
    0.15
    iral
    0.15
    ivot
    0.15
    å¶
    0.15
    hooks
    0.14
    nes
    0.14
    Äįit
    0.14
     Lon
    0.14
    Activations Density 0.006%

    No Known Activations