INDEX

Explanations

image file references and related metadata

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

nton

-0.16

erton

-0.16

-0.15

elves

-0.15

Î³Î³ÎµÎ»

-0.15

aque

-0.14

antis

-0.14

ÐµÑģÑĤÐ²

-0.14

bird

-0.14

atura

-0.14

POSITIVE LOGITS

lisi

0.16

ASC

0.16

alo

0.15

uego

0.15

ĵĺ

0.15

Ð»Ð°Ð³Ð°

0.14

svp

0.14

Ð°Ð»Ð¾Ð³

0.14

ÑĩÐ¸Ð½

0.14

untas

0.14

Activations Density 0.003%

image file references and related metadata

No Comments

No Known Activations