INDEX

Explanations

references to various types of material or content, particularly in academic or informative contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ess

-0.17

et

-0.17

oi

-0.16

pin

-0.15

ion

-0.15

ed

-0.15

 meaningful

-0.15

es

-0.15

ant

-0.15

per

-0.15

POSITIVE LOGITS

rices

0.19

zcze

0.16

nces

0.15

rese

0.15

Nob

0.15

reu

0.15

ized

0.15

ÐµÑĢÑĥ

0.14

ÏģÎ¹Î½

0.14

unately

0.14

Activations Density 0.019%

references to various types of material or content, particularly in academic or informative contexts

No Comments

No Known Activations