INDEX

Explanations

instances of the word "aussi," indicating a focus on additive or inclusive expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

antis

-0.15

zik

-0.15

hy

-0.15

aidu

-0.15

PerPixel

-0.14

Cv

-0.14

stay

-0.14

erson

-0.14

upe

-0.13

-quarter

-0.13

POSITIVE LOGITS

 convention

0.16

ufen

0.16

fos

0.15

idges

0.15

á»įng

0.15

mutable

0.15

ordion

0.14

Bra

0.14

etim

0.14

.userInteractionEnabled

0.14

Activations Density 0.004%

instances of the word "aussi," indicating a focus on additive or inclusive expressions

No Comments

No Known Activations