INDEX

Explanations

specific trends, actions, or statements that indicate importance or relevance in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

etag

-0.18

PTR

-0.15

Ð¾Ð´Ñĭ

-0.15

wers

-0.15

.Utc

-0.14

-transitional

-0.14

ngh

-0.14

æ¸

-0.14

leh

-0.13

Ã¡i

-0.13

POSITIVE LOGITS

glob

0.15

 typeid

0.15

-www

0.15

efined

0.15

Ðĭ

0.14

assel

0.13

GLOSS

0.13

arken

0.13

 Gott

0.13

alars

0.13

Activations Density 0.010%

specific trends, actions, or statements that indicate importance or relevance in a narrative

No Comments

No Known Activations