© 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. 25-LLAMASCOPE-RES-32K
    6. 22527
    Prev
    Next
    INDEX
    Explanations

    words related to farewells and emotional connections

    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
    NAL
    -0.15
    ارش
    -0.14
     réuss
    -0.13
     Enabled
    -0.12
    ç·Ĵ
    -0.12
    Realm
    -0.12
    inded
    -0.12
    letic
    -0.12
     others
    -0.12
    286
    -0.12
    POSITIVE LOGITS
     ol
    0.34
     ole
    0.28
     Mr
    0.28
     Poor
    0.26
     poor
    0.26
    Poor
    0.24
    Mr
    0.24
     dear
    0.23
     mr
    0.22
     èĢģ
    0.20
    Activations Density 0.337%

    No Known Activations