INDEX

Explanations

the word "both" indicating duality or pairings in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

orem

-0.15

igar

-0.15

isk

-0.15

åłĤ

-0.14

enha

-0.14

htdocs

-0.14

elsing

-0.13

quette

-0.13

ipple

-0.13

 nutshell

-0.13

POSITIVE LOGITS

pher

0.15

 sexes

0.14

/all

0.14

_WR

0.14

ways

0.14

poÄįet

0.14

chsel

0.14

 Traditional

0.13

 tslint

0.13

_iff

0.13

Activations Density 0.032%

the word "both" indicating duality or pairings in contexts

No Comments

No Known Activations