INDEX

Explanations

references to locations and contexts related to education and governance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

fal

-0.15

 following

-0.14

 majority

-0.13

 Oval

-0.12

eut

-0.12

COPE

-0.12

brids

-0.12

bour

-0.12

orny

-0.12

Ð¿Ð¾Ñģ

-0.12

POSITIVE LOGITS

ONGL

0.17

OKIE

0.16

/of

0.16

aves

0.14

.nlm

0.14

igh

0.14

iros

0.14

¬¸

0.14

0.13

nia

0.13

Activations Density 0.216%

references to locations and contexts related to education and governance

No Comments

No Known Activations