© 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. 16-LLAMASCOPE-RES-32K
    11. 7402
    Prev
    Next
    INDEX
    Explanations

    references to health-related weight management strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éŃĤ
    -0.19
    ossa
    -0.17
    idable
    -0.16
    inite
    -0.16
    ãĥ¼ãĤ¹
    -0.15
    osite
    -0.15
    磨
    -0.15
     Crush
    -0.14
    grave
    -0.14
     Grave
    -0.14
    POSITIVE LOGITS
    yen
    0.15
    596
    0.15
    990
    0.14
    woods
    0.14
     Gir
    0.14
    >(*
    0.14
     yem
    0.14
    olle
    0.13
    ัà¸Ĭ
    0.13
    emax
    0.13
    Activations Density 0.014%

    No Known Activations