© 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. 24-LLAMASCOPE-RES-32K
    11. 14512
    Prev
    Next
    INDEX
    Explanations

    phrases associated with achieving dreams or goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Authority
    -0.15
    foy
    -0.13
     graveyard
    -0.13
     Lem
    -0.13
    orio
    -0.13
     Bord
    -0.13
    ETS
    -0.13
    amo
    -0.12
    ets
    -0.12
    yle
    -0.12
    POSITIVE LOGITS
     true
    0.90
     True
    0.80
    true
    0.80
    True
    0.71
     TRUE
    0.71
    TRUE
    0.61
    _true
    0.59
    	true
    0.59
    (true
    0.59
    .true
    0.56
    Activations Density 0.167%

    No Known Activations