INDEX

Explanations

content related to layout structures or configurations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 láº§n

-0.16

uilder

-0.15

_CALLBACK

-0.14

alla

-0.14

Åº

-0.13

mani

-0.13

&utm

-0.13

ABL

-0.13

 Walt

-0.13

ateau

-0.13

POSITIVE LOGITS

slide

0.17

anki

0.15

 slide

0.15

 å¸ĥ

0.15

_spectrum

0.15

Ð²Ð°Ð¹

0.15

otos

0.14

lide

0.14

iesel

0.14

ewis

0.14

Activations Density 0.066%

content related to layout structures or configurations in various contexts

No Comments

No Known Activations