INDEX

Explanations

numerical data or references within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

wah

-0.15

aus

-0.14

undra

-0.14

.misc

-0.14

ÐµÑĢÐ¾

-0.14

iffin

-0.14

.Footer

-0.14

ased

-0.13

Disposition

-0.13

POSITIVE LOGITS

.zh

0.16

upo

0.16

Ã¡fico

0.16

Īĺ

0.15

Ã¡f

0.15

rado

0.15

loub

0.15

ÑĨÐ¸Ðº

0.15

_ranges

0.14

CSL

0.14

Activations Density 0.017%

numerical data or references within a text

No Comments

No Known Activations