INDEX

Explanations

terms indicating improvement or a significant presence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

è°ĵ

-0.15

ads

-0.15

&r

-0.15

Ð·Ð²

-0.15

aghan

-0.14

nh

-0.14

dus

-0.14

adm

-0.14

ampie

-0.14

_subplot

-0.14

POSITIVE LOGITS

undles

0.15

undle

0.15

Gib

0.15

 instead

0.15

onte

0.14

instead

0.14

uner

0.14

aeper

0.14

proxy

0.14

fat

0.13

Activations Density 0.344%

terms indicating improvement or a significant presence of something

No Comments

No Known Activations