INDEX

Explanations

references to specific locations or places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

erville

-0.15

reak

-0.15

EEE

-0.14

ascus

-0.13

zah

-0.13

CCI

-0.13

ngÃ¶r

-0.13

ucci

-0.13

éĩ

-0.13

ocoder

-0.13

POSITIVE LOGITS

ino

0.19

GH

0.15

erner

0.15

 munch

0.14

inus

0.14

idel

0.14

inos

0.14

ëħĢ

0.14

hen

0.14

INO

0.13

Activations Density 0.009%

references to specific locations or places

No Comments

No Known Activations

references to specific locations or places

No Comments

No Known Activations