INDEX

Explanations

phrases related to quality and performance metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 {{--<

-0.15

ivor

-0.15

ijo

-0.15

æ°

-0.14

alo

-0.14

enate

-0.14

akens

-0.14

ubi

-0.13

 Contin

-0.13

ä¿

-0.13

POSITIVE LOGITS

undy

0.16

Ð°ÑĢÐ¾Ð²

0.16

ao

0.15

çĽ¤

0.15

aign

0.15

hton

0.15

aiser

0.15

 abdom

0.14

opher

0.14

Activations Density 0.274%

phrases related to quality and performance metrics

No Comments

No Known Activations