INDEX

Explanations

references to self or personal involvement

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

atch

-0.16

.FontStyle

-0.15

illos

-0.15

 UÅ¾

-0.15

mond

-0.14

ond

-0.14

AAAA

-0.14

IMAL

-0.13

immel

-0.13

qui

-0.13

POSITIVE LOGITS

-mÃªme

0.25

zelf

0.24

zÅĳ

0.16

elves

0.15

enger

0.15

 Executor

0.14

ikat

0.14

rollo

0.14

ÑĩÐ°ÑģÐ½Ð¾

0.14

Activations Density 0.072%

references to self or personal involvement

No Comments

No Known Activations