© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 13560
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate innovation and development in education and treatment strategies

    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
    ãģ£ãģ¡
    -0.14
    avings
    -0.13
     formulation
    -0.13
     Interviews
    -0.13
    yük
    -0.13
    nivel
    -0.13
    .Expect
    -0.13
    ocy
    -0.13
    dge
    -0.13
    blick
    -0.13
    POSITIVE LOGITS
     ways
    0.71
     methods
    0.60
     Ways
    0.53
     approaches
    0.50
     techniques
    0.49
    ways
    0.49
     strategies
    0.48
     means
    0.47
    methods
    0.47
     alternatives
    0.44
    Activations Density 0.629%

    No Known Activations