© 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. 24-LLAMASCOPE-RES-32K
    11. 7730
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to studies or research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĪ
    -0.18
    ].[
    -0.17
    uesto
    -0.15
    à¹Ĥà¸Ļ
    -0.15
    orra
    -0.15
    arto
    -0.15
    ansson
    -0.15
    ç§
    -0.14
    /tos
    -0.14
    ãģĨãģ¡
    -0.14
    POSITIVE LOGITS
    amel
    0.15
    yd
    0.15
    ãĤ¿ãĥ«
    0.14
    _authentication
    0.13
    صØŃ
    0.13
    cope
    0.13
    PLICIT
    0.13
    éĥŃ
    0.13
    ystate
    0.13
    agal
    0.13
    Activations Density 0.039%

    No Known Activations