INDEX

Explanations

phrases related to recommendations and proposals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ocha

-0.16

olas

-0.14

imb

-0.14

Ð³Ð°ÑĢ

-0.14

hir

-0.14

 ÑħÐ¸Ð¼Ð¸

-0.14

attr

-0.13

iov

-0.13

=center

-0.13

POSITIVE LOGITS

recommend

0.17

utan

0.17

urs

0.16

 Aires

0.15

ivan

0.15

 prepared

0.15

acr

0.14

bone

0.14

 Bair

0.14

-tags

0.14

Activations Density 0.073%

phrases related to recommendations and proposals

No Comments

No Known Activations