INDEX

Explanations

references to lunch and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Nights

-0.21

 evenings

-0.18

 evening

-0.17

 dawn

-0.17

 nights

-0.17

 breakfast

-0.16

.za

-0.16

 night

-0.15

rena

-0.15

ensus

-0.15

POSITIVE LOGITS

time

0.33

room

0.24

ãĥ§

0.23

-time

0.22

times

0.19

box

0.19

-hour

0.18

ette

0.18

iez

0.18

ing

0.18

Activations Density 0.013%

references to lunch and related terms

No Comments

No Known Activations