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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 17769
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" and its variations, indicating a focus on deficiency or absence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    borg
    -0.16
    essen
    -0.16
    undle
    -0.15
    idel
    -0.14
    OLE
    -0.14
    cem
    -0.14
    ÄĻk
    -0.14
    otate
    -0.14
    iko
    -0.14
    issen
    -0.14
    POSITIVE LOGITS
    ada
    0.30
    lust
    0.28
    ey
    0.24
    ade
    0.18
    ened
    0.18
    nowled
    0.18
     thereof
    0.17
    nowledge
    0.17
    tiv
    0.17
    adas
    0.17
    Activations Density 0.013%

    No Known Activations