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. 16-LLAMASCOPE-RES-32K
    6. 21737
    Prev
    Next
    INDEX
    Explanations

    topics related to criminal justice and release from incarceration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UME
    -0.14
     Tome
    -0.14
    inne
    -0.14
    amaged
    -0.14
     resc
    -0.14
    udent
    -0.14
    ume
    -0.14
    _DF
    -0.13
    umes
    -0.13
    kea
    -0.13
    POSITIVE LOGITS
     prison
    0.29
     sentenced
    0.25
     sentence
    0.25
     jail
    0.24
     parole
    0.22
    arcer
    0.22
     serving
    0.21
    sentence
    0.21
     incarcerated
    0.20
     release
    0.20
    Activations Density 0.171%

    No Known Activations