INDEX

Explanations

terms and phrases related to numerical values and scoring

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

-0.14

itters

-0.14

ced

-0.14

amina

-0.14

 COPYING

-0.14

ubu

-0.14

 courtesy

-0.14

æµ®

-0.14

GOT

-0.14

birth

-0.13

POSITIVE LOGITS

yne

0.17

errat

0.16

 Freeman

0.14

èĨ

0.14

erval

0.14

 Convention

0.14

ORTH

0.14

0.13

orth

0.13

rok

0.13

Activations Density 0.007%

terms and phrases related to numerical values and scoring

No Comments

No Known Activations