INDEX

Explanations

expressions of gratitude and acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

 Giov

-0.18

ingly

-0.14

Ear

-0.14

çĥ

-0.14

-ing

-0.14

é§

-0.14

bole

-0.14

odash

-0.13

orate

-0.13

ogram

-0.13

POSITIVE LOGITS

olla

0.15

 Amateur

0.15

 Rubin

0.14

ãĥ«ãĤ¯

0.14

olin

0.14

#__

0.14

osemite

0.14

tid

0.14

ello

0.14

Activations Density 0.011%

expressions of gratitude and acknowledgment

No Comments

No Known Activations