INDEX

Explanations

sentences expressing uncertainty or a lack of knowledge about choices and directions

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

Negative Logits

kem

-0.15

 personn

-0.14

 recap

-0.14

ÏĦÏĥÎ¹

-0.14

oro

-0.14

alchemy

-0.14

ve

-0.13

Extern

-0.13

allo

-0.13

_ANY

-0.13

POSITIVE LOGITS

 exactly

0.38

 Exactly

0.27

Exactly

0.27

 precisely

0.25

bow

0.22

 where

0.20

 genau

0.19

 which

0.18

if

0.18

 whether

0.18

Activations Density 0.108%

sentences expressing uncertainty or a lack of knowledge about choices and directions

No Known Activations