© 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. 17133
    Prev
    Next
    INDEX
    Explanations

    phrases related to social responsibility and ethical considerations

    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
    onica
    -0.16
    ãĥ¼ãĥĵ
    -0.15
    OffsetTable
    -0.15
    ivec
    -0.15
    edes
    -0.15
    IVA
    -0.15
    onium
    -0.14
    ancode
    -0.14
    esModule
    -0.13
    imler
    -0.13
    POSITIVE LOGITS
    sg
    0.20
    enge
    0.15
    наÑĩе
    0.15
    ALA
    0.14
    obe
    0.14
     requis
    0.14
    /request
    0.14
    881
    0.14
    ness
    0.14
    orem
    0.14
    Activations Density 0.005%

    No Known Activations