INDEX

Explanations

phrases or words indicating purpose or intention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

Tod

-0.17

aire

-0.17

-0.16

ijd

-0.16

ration

-0.15

Nug

-0.15

usercontent

-0.15

corp

-0.15

forth

-0.15

POSITIVE LOGITS

Ngh

0.15

embre

0.14

leton

0.14

 Pleasant

0.14

 Detective

0.14

Ð¾Ð¼Ð°

0.14

AGR

0.14

 Furn

0.14

Î¼Î·

0.14

 Eins

0.13

Activations Density 0.006%

phrases or words indicating purpose or intention

No Comments

No Known Activations