© 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. 17849
    Prev
    Next
    INDEX
    Explanations

    emotive expressions or strong sentiments in discourse

    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
    OffsetTable
    -0.19
    FunctionFlags
    -0.16
    InitStruct
    -0.15
    Labels
    -0.14
    GenerationStrategy
    -0.14
    InputBorder
    -0.14
    )(__
    -0.14
    µľ
    -0.13
     automát
    -0.13
    ÑĦÑĦ
    -0.13
    POSITIVE LOGITS
    ly
    0.16
     tslint
    0.16
    Äħd
    0.16
    lose
    0.14
    rador
    0.14
    ød
    0.14
    bla
    0.13
    ...
    0.13
    анÑĤаж
    0.13
    çĦ¶
    0.13
    Activations Density 0.052%

    No Known Activations