© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 26-LLAMASCOPE-RES-32K
    6. 6304
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Nach."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶Į
    -0.18
    BITS
    -0.17
    hlen
    -0.16
    atcher
    -0.15
    stakes
    -0.15
    ASSES
    -0.15
    630
    -0.14
    otto
    -0.14
    .dy
    -0.14
    änder
    -0.14
    POSITIVE LOGITS
    fol
    0.24
    ward
    0.24
    dem
    0.23
    ts
    0.20
    wards
    0.20
    -effects
    0.20
    weis
    0.19
    tk
    0.18
    tm
    0.18
     completion
    0.18
    Activations Density 0.009%

    No Known Activations