INDEX

Explanations

instances of punctuation marks, particularly dashes and ellipses, in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

acman

-0.16

åķ

-0.16

ause

-0.15

IGHL

-0.15

ife

-0.15

SOLE

-0.14

eed

-0.14

.dense

-0.14

aspers

-0.14

oul

-0.14

POSITIVE LOGITS

oret

0.17

-uppercase

0.15

sdale

0.14

 -*-č↵

0.13

 hence

0.13

 equals

0.13

fx

0.13

ayah

0.13

wiki

0.13

 both

0.13

Activations Density 0.121%

instances of punctuation marks, particularly dashes and ellipses, in the text

No Comments

No Known Activations