INDEX

Explanations

possessive pronouns indicating ownership or relation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

-0.17

Ã¶g

-0.15

ãĥĨãĥ«

-0.13

uilder

-0.13

 Ãĸr

-0.13

OMEM

-0.13

 Ð´ÑĢ

-0.13

ÙĬØ¹

-0.13

æŁĶ

-0.13

POSITIVE LOGITS

 ability

0.21

 role

0.19

Ð³Ñĥ

0.17

á»ĭ

0.17

 attempt

0.16

 tendency

0.16

 attempts

0.15

 ÑģÐ¿Ð¾ÑģÐ¾Ð±

0.15

 inability

0.15

 handling

0.15

Activations Density 0.169%

possessive pronouns indicating ownership or relation

No Comments

No Known Activations