INDEX

Explanations

phrases indicating the beginning of a process or action steps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

iu

-0.17

ugo

-0.16

aha

-0.15

 bait

-0.15

ãĤ¦ãĥĪ

-0.14

ocs

-0.14

agon

-0.14

æīį

-0.14

iology

-0.13

asser

-0.13

POSITIVE LOGITS

azen

0.15

zano

0.15

 Conversation

0.14

indi

0.14

ÏĦÏħ

0.14

atori

0.14

ç·¨

0.14

/licenses

0.14

AME

0.14

versations

0.14

Activations Density 0.104%

phrases indicating the beginning of a process or action steps

No Comments

No Known Activations