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. 27-LLAMASCOPE-RES-32K
    6. 7
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualifications and experience for job applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appa
    -0.18
    ValueCollection
    -0.17
    mana
    -0.17
    ropp
    -0.15
    230
    -0.14
     Ñĩого
    -0.14
    ANJI
    -0.14
    esome
    -0.14
    uddled
    -0.13
    ÙĪØ¹
    -0.13
    POSITIVE LOGITS
     relaxation
    0.22
     relax
    0.21
     Relax
    0.18
     relaxed
    0.17
     relaxing
    0.17
    ivant
    0.15
    .Age
    0.15
     Passed
    0.15
     aggregate
    0.15
     poss
    0.15
    Activations Density 0.010%

    No Known Activations