INDEX

Explanations

expressions related to making choices or selecting options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

hu

-0.14

thed

-0.14

ighton

-0.14

ly

-0.13

 Ð¾Ð±Ð»

-0.13

è²¸

-0.13

æĩ

-0.13

à¥ĭà¤§

-0.13

å¿ľ

-0.13

POSITIVE LOGITS

for

0.17

ains

0.15

entially

0.15

-for

0.15

ske

0.15

-out

0.14

 OPTION

0.14

unist

0.14

-in

0.14

Activations Density 0.010%

expressions related to making choices or selecting options

No Comments

No Known Activations