© 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. 13-LLAMASCOPE-RES-32K
    11. 15626
    Prev
    Next
    INDEX
    Explanations

    references to characters, names, and roles in a narrative or story context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lenme
    -0.17
     поÑħ
    -0.15
    alama
    -0.15
    ÅĻi
    -0.14
    ilton
    -0.14
    ôme
    -0.14
    owo
    -0.14
    .dsl
    -0.14
    -bs
    -0.14
    姿
    -0.14
    POSITIVE LOGITS
     infos
    0.14
     Pickup
    0.14
    /disc
    0.14
     Patel
    0.13
     Morrow
    0.13
     vill
    0.13
    pest
    0.13
     vil
    0.13
    luck
    0.13
     opposite
    0.13
    Activations Density 0.295%

    No Known Activations