INDEX

Explanations

references to a character named Sarah

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

tti

-0.17

kor

-0.15

ega

-0.15

aal

-0.14

 Roose

-0.14

che

-0.14

luk

-0.14

irty

-0.14

rav

-0.14

ardo

-0.14

POSITIVE LOGITS

 Jane

0.19

 Palin

0.19

Jane

0.18

acen

0.17

æ¢¨

0.17

ertz

0.17

 plain

0.17

cuda

0.16

ãĥªãĤ«

0.16

Beth

0.16

Activations Density 0.010%

references to a character named Sarah

No Comments

No Known Activations