INDEX

Explanations

references to authors and significant contributors in a literary or academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Ã³m

-0.17

å·»

-0.14

wick

-0.14

 Tato

-0.14

ÏĬÎº

-0.14

 Directed

-0.14

NCY

-0.14

Ð½Ð¾ÑģÑı

-0.14

",-

-0.13

POSITIVE LOGITS

et

0.19

Untitled

0.15

istory

0.14

_IMAGES

0.14

.github

0.14

ullah

0.14

ed

0.14

istor

0.13

generic

0.13

 Ð²ÐºÐ»Ð°Ð´

0.13

Activations Density 0.257%

references to authors and significant contributors in a literary or academic context

No Comments

No Known Activations