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. 24-LLAMASCOPE-RES-32K
    6. 15281
    Prev
    Next
    INDEX
    Explanations

    references to sexual assault allegations and testimonies related to prominent individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Victims
    -0.16
    outil
    -0.16
    ismet
    -0.16
    audi
    -0.15
    ideon
    -0.15
     sond
    -0.15
    InputBorder
    -0.15
    اÙģØª
    -0.15
    GuidId
    -0.15
    annonce
    -0.14
    POSITIVE LOGITS
     charge
    0.56
     charges
    0.56
     allegations
    0.55
     allegation
    0.53
     accusations
    0.48
     alleged
    0.47
     accusation
    0.46
     claims
    0.45
     Charge
    0.44
     charged
    0.43
    Activations Density 0.155%

    No Known Activations