INDEX

Explanations

words and phrases related to self-presentation and identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

.ci

-0.14

à¤¦à¤®

-0.14

wa

-0.13

quelle

-0.13

acias

-0.13

ãĤ¤ãĥ¤

-0.13

Ø§Ø¹Ø¨

-0.13

outines

-0.13

itas

-0.13

.kotlin

-0.13

POSITIVE LOGITS

_the

0.21

-the

0.21

the

0.18

/the

0.15

The

0.15

atoi

0.14

thew

0.14

ithe

0.14

THE

0.14

The

0.13

Activations Density 0.106%

words and phrases related to self-presentation and identity

No Comments

No Known Activations