INDEX

Explanations

technical and procedural language related to systems and policies

oai_token-act-pair · gpt-4o-mini Triggered 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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

UGE

-0.16

IMIT

-0.15

 quite

-0.14

HECK

-0.14

addock

-0.13

 ráº¥t

-0.13

 Quite

-0.13

 part

-0.13

 another

-0.13

 restless

-0.13

POSITIVE LOGITS

 appropriate

0.63

 proper

0.61

 adequate

0.57

appropriate

0.56

proper

0.51

 suitable

0.48

 correct

0.44

ropriate

0.43

 adec

0.43

æŃ£ç¡®

0.41

Activations Density 1.062%

technical and procedural language related to systems and policies

No Comments

No Known Activations