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. 25-LLAMASCOPE-RES-32K
    6. 10647
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal charges and criminal activity

    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
    ambre
    -0.17
     stump
    -0.15
     murders
    -0.15
    arget
    -0.15
    _CF
    -0.14
    orgen
    -0.14
    abay
    -0.14
    essler
    -0.14
    اÛĮ
    -0.13
     nap
    -0.13
    POSITIVE LOGITS
     Disorder
    0.23
     disorder
    0.23
     Poss
    0.23
     possession
    0.21
    hind
    0.19
     Resist
    0.19
    peater
    0.19
     Battery
    0.18
     resisting
    0.17
    Poss
    0.17
    Activations Density 0.030%

    No Known Activations