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. 19-LLAMASCOPE-RES-32K
    6. 29391
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly focusing on the name "Brendan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AFX
    -0.15
    alcon
    -0.15
     оÑĤв
    -0.15
     GOODMAN
    -0.15
     punct
    -0.15
    pler
    -0.14
    çĽĺ
    -0.14
    ningen
    -0.14
     opcode
    -0.14
     punctuation
    -0.14
    POSITIVE LOGITS
     Irish
    0.25
     Ireland
    0.25
    patrick
    0.21
     Conor
    0.20
    .ie
    0.20
     Dublin
    0.18
     Brendan
    0.18
    ews
    0.17
     Gallagher
    0.17
     sean
    0.17
    Activations Density 0.047%

    No Known Activations