© 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. 26-LLAMASCOPE-RES-32K
    11. 28084
    Prev
    Next
    INDEX
    Explanations

    content related to the entertainment industry and its productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opian
    -0.16
     Programming
    -0.15
    élé
    -0.15
    ersonic
    -0.14
     equ
    -0.14
    ikki
    -0.14
    loh
    -0.14
    ique
    -0.14
     Dah
    -0.14
     Hart
    -0.14
    POSITIVE LOGITS
    Ghost
    0.41
     Ghost
    0.41
     ghost
    0.38
    _ghost
    0.35
    ghost
    0.35
     ghosts
    0.33
     proton
    0.27
    busters
    0.24
     paranormal
    0.21
    éľĬ
    0.19
    Activations Density 0.003%

    No Known Activations