INDEX

Explanations

references to motivation and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ed

-0.20

edly

-0.19

ald

-0.19

iw

-0.17

edy

-0.17

ey

-0.17

esh

-0.17

liness

-0.16

.au

-0.16

ratulations

-0.16

POSITIVE LOGITS

ized

0.20

ting

0.19

REFERRED

0.18

ization

0.17

ational

0.17

imestep

0.17

umblr

0.17

self

0.16

atively

0.15

ally

0.15

Activations Density 0.058%

references to motivation and related concepts

No Comments

No Known Activations