INDEX

Explanations

phrases that convey uncertainty or speculation

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

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vro

-0.18

argent

-0.16

iddles

-0.15

noch

-0.15

Î¼Î¯

-0.14

ãĥ³ãĥĢ

-0.14

ocate

-0.14

/compiler

-0.13

upro

-0.13

erguson

-0.13

POSITIVE LOGITS

 sounds

1.02

 Sounds

0.91

 sound

0.90

sounds

0.89

Sounds

0.89

 sounded

0.81

 Sound

0.76

 sounding

0.76

sound

0.75

Sound

0.73

Activations Density 0.225%

phrases that convey uncertainty or speculation

No Comments

No Known Activations