INDEX

Explanations

instances of inability or challenges expressed through the use of "can't" and "cannot."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 -*-č↵

-0.15

ãĥĬãĥ¼

-0.15

 domicile

-0.15

erv

-0.14

fad

-0.14

udi

-0.14

hl

-0.14

chez

-0.14

 stud

-0.13

stud

-0.13

POSITIVE LOGITS

 afford

0.23

 stomach

0.20

 figure

0.20

 find

0.19

 finds

0.17

 drum

0.17

find

0.17

 FIND

0.16

/find

0.15

elsen

0.15

Activations Density 0.157%

instances of inability or challenges expressed through the use of "can't" and "cannot."

No Comments

No Known Activations