© 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. 20-LLAMASCOPE-RES-32K
    11. 31656
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns in reference to individuals involved in incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    άνι
    -0.15
    osg
    -0.15
    abelle
    -0.14
    Ðĭ
    -0.14
     Candidates
    -0.14
     hled
    -0.14
    emachine
    -0.14
    ichel
    -0.14
     Crack
    -0.13
    游
    -0.13
    POSITIVE LOGITS
     fate
    0.22
     handlers
    0.18
     status
    0.18
     predic
    0.18
     employers
    0.18
     condition
    0.17
     attackers
    0.17
    handlers
    0.17
     plight
    0.17
     story
    0.17
    Activations Density 0.192%

    No Known Activations