INDEX

Explanations

mathematical indices and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

iyim

-0.19

aylight

-0.17

SWEP

-0.16

lopen

-0.16

anou

-0.15

ÅĽnie

-0.15

:@""

-0.15

_ARB

-0.15

RESSED

-0.15

engl

-0.15

POSITIVE LOGITS

iw

0.18

ery

0.18

ers

0.16

0.15

ìĤ¬íķŃ

0.15

or

0.15

uras

0.15

run

0.14

Activations Density 0.066%

mathematical indices and their relationships

No Comments

No Known Activations