INDEX

Explanations

terms associated with restrictions, conditions, and various types of classifications

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

-0.14

ÑĢÐ°Ð´Ð¸

-0.14

inke

-0.13

loo

-0.13

 Garner

-0.13

apple

-0.13

dsl

-0.13

.au

-0.12

Fre

-0.12

ql

-0.12

POSITIVE LOGITS

ness

0.14

à¸¯

0.14

imate

0.14

igi

0.14

åĨ

0.13

olia

0.13

reed

0.13

ities

0.13

 reckon

0.13

imated

0.13

Activations Density 0.164%

terms associated with restrictions, conditions, and various types of classifications

No Comments

No Known Activations