INDEX

Explanations

words describing a lack of clarity or vagueness

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

isa

-0.17

 Goth

-0.15

avn

-0.15

lew

-0.15

antis

-0.15

æµģéĩı

-0.15

avez

-0.14

anean

-0.14

èĤ¥

-0.14

-toggler

-0.14

POSITIVE LOGITS

cape

0.17

0.16

atem

0.16

Hin

0.15

 Ridley

0.14

Ã³st

0.14

wand

0.14

 Birch

0.14

insula

0.13

 Dense

0.13

Activations Density 0.007%

words describing a lack of clarity or vagueness

No Comments

No Known Activations