INDEX

Explanations

references to funding sources and research support

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

usan

-0.18

itters

-0.16

ekil

-0.15

prec

-0.14

 Prec

-0.14

Prec

-0.14

flation

-0.13

nom

-0.13

 Rivera

-0.13

_visibility

-0.13

POSITIVE LOGITS

avern

0.16

ByUrl

0.16

 fisse

0.16

ÑĢÐ°ÑģÑĤÐ°

0.15

buc

0.15

.hom

0.15

veau

0.15

 Ð³ÑĥÐ±ÐµÑĢ

0.14

vest

0.14

utral

0.14

Activations Density 0.087%

references to funding sources and research support

No Comments

No Known Activations