© 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. 16052
    Prev
    Next
    INDEX
    Explanations

    words and phrases with the letter 'a' in them

    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
    bon
    -0.18
    cts
    -0.18
    th
    -0.18
    bid
    -0.18
    j
    -0.18
    lp
    -0.17
    bble
    -0.17
    ct
    -0.17
    ir
    -0.17
    ater
    -0.17
    POSITIVE LOGITS
     partir
    0.22
     través
    0.20
    credit
    0.20
    fort
    0.19
    isl
    0.19
    grav
    0.19
    propri
    0.18
    prob
    0.17
    моÑĢ
    0.17
    minor
    0.17
    Activations Density 0.014%

    No Known Activations