© 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. 17-LLAMASCOPE-RES-32K
    11. 16078
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or programs related to technology and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eel
    -0.14
    utzer
    -0.13
    olars
    -0.13
    æ
    -0.13
    _beg
    -0.13
    thag
    -0.13
     Sle
    -0.13
    \Backend
    -0.12
    atile
    -0.12
     summed
    -0.12
    POSITIVE LOGITS
     folks
    0.17
     Fol
    0.16
     typically
    0.15
     supporting
    0.14
    Typ
    0.14
    amo
    0.14
    captures
    0.14
     caric
    0.14
     Telefon
    0.14
    ession
    0.14
    Activations Density 1.047%

    No Known Activations