INDEX

Explanations

references to quantities, classifications, and conditions

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ese

-0.15

 traces

-0.15

chor

-0.15

sep

-0.14

bit

-0.14

 Trace

-0.14

POSITIVE LOGITS

TRGL

0.17

artment

0.17

anner

0.16

strup

0.16

áº©y

0.16

(CG

0.15

undo

0.15

é³´

0.15

lexport

0.15

ernote

0.14

Activations Density 0.273%

references to quantities, classifications, and conditions

No Known Activations