INDEX

Explanations

information related to academic programs and workshops

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

idon

-0.14

ilig

-0.14

 light

-0.14

utsch

-0.14

ISC

-0.13

ennen

-0.13

IPC

-0.13

 diam

-0.13

ANGLE

-0.13

ivet

-0.13

POSITIVE LOGITS

atel

0.17

 grant

0.16

 ÐľÐ°ÐºÑģÐ¸Ð¼

0.15

anki

0.15

bil

0.15

roys

0.14

 research

0.14

PIO

0.14

 gezocht

0.14

 Budd

0.14

Activations Density 0.007%

information related to academic programs and workshops

No Comments

No Known Activations