Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 18933
    Prev
    Next
    INDEX
    Explanations

    strong references to labeling and packaging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Linkedin
    -0.17
     Loft
    -0.15
     Ling
    -0.15
    رÙĪÙħ
    -0.15
     Logan
    -0.15
     Rom
    -0.15
     Lottery
    -0.15
     Lion
    -0.14
     Lucy
    -0.14
    LinkedIn
    -0.14
    POSITIVE LOGITS
     label
    1.08
     Label
    0.95
    label
    0.93
     labels
    0.93
    -label
    0.92
    Label
    0.89
    _label
    0.87
    .label
    0.85
     LABEL
    0.83
     Labels
    0.79
    Activations Density 0.101%

    No Known Activations