INDEX

Explanations

mentions of researchers and scientific authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 claim

-0.16

claim

-0.16

 Claims

-0.15

IFT

-0.15

 claims

-0.14

 CLAIM

-0.14

Ľ°

-0.14

 Claim

-0.14

ipa

-0.14

udo

-0.13

POSITIVE LOGITS

å¥ĳ

0.16

 ÑĩÐ¾ÑĢ

0.15

 methyl

0.15

ACA

0.14

 meth

0.14

erer

0.14

ÑĢÐ¾Ñĩ

0.14

 prelim

0.14

aca

0.14

 Dong

0.14

Activations Density 0.002%

mentions of researchers and scientific authors

No Comments

No Known Activations

mentions of researchers and scientific authors

No Comments

No Known Activations