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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 30-LLAMASCOPE-RES-32K
    6. 23399
    Prev
    Next
    INDEX
    Explanations

    themes related to self-sacrifice and altruism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .scalablytyped
    -0.15
     SPDX
    -0.14
    ikel
    -0.14
    ]={↵
    -0.13
    νη
    -0.13
    roud
    -0.13
    jal
    -0.13
    ÃŃÅ¡e
    -0.13
    ickets
    -0.13
    ope
    -0.13
    POSITIVE LOGITS
     sacrifice
    0.60
     sacrifices
    0.55
     Sacr
    0.52
     sacrific
    0.52
     sacrificed
    0.52
     sacrificing
    0.51
     sacr
    0.51
     sac
    0.46
     SAC
    0.44
     trade
    0.38
    Activations Density 0.192%

    No Known Activations