Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 6781
    Prev
    Next
    INDEX
    Explanations

    expressions related to caring or lack of caring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oris
    -0.18
    ovie
    -0.15
    ramework
    -0.14
    ensing
    -0.14
    eping
    -0.14
    ardo
    -0.14
    ora
    -0.14
    ood
    -0.14
    gra
    -0.14
    orf
    -0.14
    POSITIVE LOGITS
     about
    0.26
     cared
    0.23
     whether
    0.22
    lessly
    0.22
     enough
    0.21
     care
    0.19
     deeply
    0.18
     cares
    0.18
     tentang
    0.17
     caring
    0.17
    Activations Density 0.028%

    No Known Activations