INDEX

Explanations

the word "either" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

vla

-0.16

vv

-0.15

vb

-0.14

rsa

-0.14

nes

-0.14

sci

-0.14

ssp

-0.14

ebo

-0.14

vak

-0.14

acco

-0.14

POSITIVE LOGITS

wel

0.21

phans

0.21

anged

0.19

theless

0.17

-than

0.17

 EITHER

0.17

either

0.16

 either

0.16

anges

0.15

angs

0.15

Activations Density 0.026%

the word "either" and its variations in different contexts

No Comments

No Known Activations