© 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. 25-LLAMASCOPE-RES-32K
    11. 18411
    Prev
    Next
    INDEX
    Explanations

    conditional phrases related to offers of help or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocument
    -0.15
    姫
    -0.14
    WEBPACK
    -0.14
    Æ°á»Ŀi
    -0.14
    ê²
    -0.14
     Struct
    -0.13
     MER
    -0.13
    kie
    -0.13
    _WARNINGS
    -0.13
    onus
    -0.13
    POSITIVE LOGITS
     interest
    0.31
     interested
    0.30
     interes
    0.29
     Interested
    0.27
     interess
    0.26
    interested
    0.25
     Interest
    0.24
     intéress
    0.24
     interests
    0.23
    interest
    0.23
    Activations Density 0.067%

    No Known Activations