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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 17054
    Prev
    Next
    INDEX
    Explanations

    occurrences of negative adjectives and phrases describing malevolent traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     canv
    -0.14
     Latter
    -0.14
    au
    -0.14
     namedtuple
    -0.14
    er
    -0.14
    ourse
    -0.14
    ij
    -0.14
    is
    -0.14
    ognito
    -0.14
     eid
    -0.14
    POSITIVE LOGITS
    illac
    0.21
     jadx
    0.17
     addCriterion
    0.16
    areth
    0.16
    .fm
    0.15
     пал
    0.15
     ldb
    0.15
    arkan
    0.15
    PTS
    0.15
    ObjectContext
    0.14
    Activations Density 0.024%

    No Known Activations