© 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. 19-LLAMASCOPE-RES-32K
    11. 29803
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "purpose" and its variations, indicating a focus on intention or meaning behind actions

    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
    redo
    -0.18
    orna
    -0.18
    áj
    -0.17
    red
    -0.16
    ish
    -0.15
    å¯
    -0.15
    rec
    -0.15
    ey
    -0.15
    len
    -0.15
    lay
    -0.14
    POSITIVE LOGITS
    fully
    0.32
    ful
    0.28
    -built
    0.24
    FUL
    0.23
    fulness
    0.21
    lessly
    0.17
    quoi
    0.16
     tw
    0.15
    arily
    0.15
    pendicular
    0.15
    Activations Density 0.019%

    No Known Activations