© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 31988
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "im," indicating a focus on words relating to immateriality or negation

    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
    er
    -0.33
    leri
    -0.26
    mer
    -0.26
    on
    -0.24
    m
    -0.24
    al
    -0.24
    o
    -0.24
    erli
    -0.23
    g
    -0.23
    b
    -0.23
    POSITIVE LOGITS
    mediate
    0.19
    ply
    0.19
    mediately
    0.19
    agine
    0.18
    proved
    0.18
    ensions
    0.18
    perial
    0.17
    prove
    0.17
    possible
    0.17
    ilarity
    0.17
    Activations Density 0.029%

    No Known Activations