INDEX

Explanations

mathematical definitions and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

sters

-0.18

agent

-0.15

Î¼Î²

-0.14

ston

-0.14

ster

-0.14

pson

-0.13

akens

-0.13

bers

-0.13

ormap

-0.13

aj

-0.13

POSITIVE LOGITS

bos

0.17

.scalablytyped

0.15

mot

0.14

Collision

0.14

/mac

0.14

bel

0.14

gre

0.13

Tu

0.13

zsche

0.13

idden

0.13

Activations Density 0.056%

mathematical definitions and notations

No Comments

No Known Activations