INDEX

Explanations

phrases that express uncertainty or questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-blog

-0.14

 patter

-0.14

 Leban

-0.14

ameda

-0.14

isbn

-0.14

izu

-0.14

ReturnType

-0.13

isu

-0.13

 blog

-0.13

illis

-0.13

POSITIVE LOGITS

Via

0.19

READ

0.19

Via

0.18

via

0.18

NEXT

0.18

SHARE

0.18

.Source

0.17

RELATED

0.17

via

0.17

VIA

0.16

Activations Density 0.074%

phrases that express uncertainty or questioning

No Comments

No Known Activations