INDEX

Explanations

references to geographical regions and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

insky

-0.19

inks

-0.15

ipo

-0.14

Î¾

-0.14

prung

-0.14

ibu

-0.14

eda

-0.13

inking

-0.13

ennes

-0.13

ãģ£ãģ¦

-0.13

POSITIVE LOGITS

0.18

Å¼e

0.17

utzer

0.16

 Ground

0.16

 ground

0.15

Hur

0.15

-ground

0.14

rome

0.14

 flesh

0.14

Activations Density 0.264%

references to geographical regions and classifications

No Comments

No Known Activations