INDEX

Explanations

references to academic publications and research contributions

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

formats

-0.16

 DÃ¼n

-0.15

apesh

-0.15

anchor

-0.14

 anchor

-0.14

bette

-0.14

 format

-0.14

 formats

-0.14

utton

-0.14

anchors

-0.14

POSITIVE LOGITS

Dean

0.19

 Dean

0.18

faculty

0.18

 faculty

0.18

 vice

0.18

 Branch

0.18

 King

0.18

 Vice

0.18

 Faculty

0.17

 Pure

0.17

Activations Density 0.018%

references to academic publications and research contributions

No Comments

No Known Activations