INDEX

Explanations

time references and schedules

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ello

-0.18

estre

-0.17

aeda

-0.15

 Meyer

-0.15

anke

-0.15

ilmington

-0.14

eyer

-0.14

 Stretch

-0.14

URN

-0.13

 Maid

-0.13

POSITIVE LOGITS

 aÅ¾

0.19

 hour

0.18

 until

0.17

 till

0.17

 Hour

0.16

_until

0.15

-hour

0.15

 late

0.15

 Äĳáº¿n

0.15

 hours

0.15

Activations Density 0.019%

time references and schedules

No Comments

No Known Activations