INDEX

Explanations

numerical data related to measurements or statistics

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

ules

-0.18

 latter

-0.17

peÄį

-0.16

ERICA

-0.13

orton

-0.13

 hint

-0.13

ity

-0.13

 contradiction

-0.13

 cave

-0.13

PASS

-0.13

POSITIVE LOGITS

anst

0.16

bles

0.15

lech

0.14

ë§¹

0.14

alama

0.14

defs

0.14

Queryable

0.14

iÃªn

0.14

AUSE

0.13

.gf

0.13

Activations Density 0.084%

numerical data related to measurements or statistics

No Comments

No Known Activations