INDEX

Explanations

the name "Henry" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

enge

-0.20

nap

-0.15

deck

-0.15

tega

-0.15

chwitz

-0.14

ãĥ¥ãĥ¼

-0.14

argent

-0.14

uros

-0.14

å¤ĩ

-0.14

pearance

-0.14

POSITIVE LOGITS

etta

0.32

0.24

 Clay

0.21

kÃ³w

0.20

 VIII

0.18

 Kiss

0.17

 clay

0.17

Cav

0.16

 kiss

0.15

igar

0.15

Activations Density 0.012%

the name "Henry" in various contexts

No Comments

No Known Activations