© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 10559
    Prev
    Next
    INDEX
    Explanations

    words or prefixes that denote negativity or unkindness

    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
    778
    -0.15
    _visibility
    -0.14
     U
    -0.14
     anonymity
    -0.14
     Le
    -0.13
    visibility
    -0.13
     budd
    -0.13
    293
    -0.13
    rai
    -0.13
    964
    -0.13
    POSITIVE LOGITS
    ecessarily
    0.23
    conv
    0.22
    help
    0.20
    character
    0.19
    bec
    0.19
    accept
    0.18
    nce
    0.18
    wise
    0.18
    trust
    0.18
    enth
    0.17
    Activations Density 0.027%

    No Known Activations