© 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. 15-LLAMASCOPE-RES-32K
    11. 1966
    Prev
    Next
    INDEX
    Explanations

    content related to television series seasons and episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èIJ½ãģ¡
    -0.17
    owns
    -0.15
    avian
    -0.15
    vier
    -0.15
    ofire
    -0.15
    _simps
    -0.15
     pang
    -0.15
    à¥įयम
    -0.15
    oting
    -0.15
    \Has
    -0.14
    POSITIVE LOGITS
    ellido
    0.16
    anson
    0.15
     éŁĵ
    0.14
    ius
    0.13
    áÅĻ
    0.13
     Benson
    0.13
     meaning
    0.13
    pro
    0.13
    yk
    0.13
    acz
    0.13
    Activations Density 0.126%

    No Known Activations