© 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. 31-LLAMASCOPE-RES-32K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    references to interrogation and torture in a governmental context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aar
    -0.14
    andom
    -0.14
    icros
    -0.13
    ãĥ³ãĥĹ
    -0.13
    oupon
    -0.13
    паÑĤ
    -0.13
     Consumers
    -0.13
     borough
    -0.13
    umer
    -0.13
    ommen
    -0.13
    POSITIVE LOGITS
     interrogation
    0.39
     torture
    0.39
     interrog
    0.37
     water
    0.31
     Tort
    0.30
     TORT
    0.30
     tort
    0.29
     CIA
    0.28
     techniques
    0.28
     tortured
    0.25
    Activations Density 0.017%

    No Known Activations