INDEX

Explanations

conditional phrases indicating options or alternatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

osu

-0.16

Extra

-0.16

chwitz

-0.15

aÅ¾

-0.14

asca

-0.14

INC

-0.14

_FAR

-0.14

ovny

-0.14

ICLE

-0.13

Ã¤nder

-0.13

POSITIVE LOGITS

 equivalent

0.35

 Equivalent

0.27

 equivalents

0.26

 equival

0.26

ients

0.21

yx

0.21

Equivalent

0.20

ignal

0.18

ien

0.18

 alternative

0.17

Activations Density 0.108%

conditional phrases indicating options or alternatives

No Comments

No Known Activations