© 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. 17016
    Prev
    Next
    INDEX
    Explanations

    terms related to fiduciary responsibilities and actions

    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
    er
    -0.27
    ey
    -0.25
    erb
    -0.23
    eh
    -0.21
    s
    -0.20
    eyn
    -0.20
    eye
    -0.19
    i
    -0.19
    eria
    -0.19
    ek
    -0.18
    POSITIVE LOGITS
    irectional
    0.30
    imensional
    0.24
    extr
    0.23
    der
    0.23
    gewater
    0.21
    entities
    0.21
    eways
    0.20
    imension
    0.20
    iot
    0.20
    elines
    0.20
    Activations Density 0.054%

    No Known Activations