© 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. 29-LLAMASCOPE-RES-32K
    11. 17775
    Prev
    Next
    INDEX
    Explanations

    comparative judgments about authenticity and quality in various contexts

    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
    ģm
    -0.13
    ARK
    -0.13
    ImageSharp
    -0.13
    бÑĥдÑĮ
    -0.13
    ãĤĵãģ¨
    -0.12
    -transitional
    -0.12
    onian
    -0.12
    baugh
    -0.12
    ùy
    -0.12
    -valu
    -0.12
    POSITIVE LOGITS
     real
    1.23
    real
    1.00
     REAL
    0.93
     actual
    0.88
     Real
    0.87
    -real
    0.86
    Real
    0.84
    _real
    0.82
    REAL
    0.80
    (real
    0.78
    Activations Density 0.727%

    No Known Activations