© 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. 5-LLAMASCOPE-RES-32K
    6. 18903
    Prev
    Next
    INDEX
    Explanations

    instances of various forms of the word "no" and its negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    921
    -0.15
    760
    -0.15
    712
    -0.14
    ONT
    -0.14
    XY
    -0.14
     Russell
    -0.14
    esan
    -0.14
    CHAT
    -0.14
    ient
    -0.14
    608
    -0.14
    POSITIVE LOGITS
    quam
    0.14
    habit
    0.14
    éģķãģĦ
    0.14
    ovky
    0.14
    ëłī
    0.14
    own
    0.13
    iqueta
    0.13
    ãģŁãĤģãģ®
    0.13
    ÙĦاÙĦ
    0.13
    bones
    0.13
    Activations Density 0.024%

    No Known Activations