INDEX

Explanations

numeric symbols and special characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

FRING

-0.17

bras

-0.15

arias

-0.15

ativos

-0.15

plusplus

-0.15

arding

-0.14

ativo

-0.14

issors

-0.14

ativa

-0.14

 Orth

-0.14

POSITIVE LOGITS

zi

0.18

ETA

0.15

zung

0.15

IMA

0.15

ETS

0.14

 Freed

0.14

trys

0.14

spir

0.14

0.13

 accord

0.13

Activations Density 0.042%

numeric symbols and special characters in the text

No Comments

No Known Activations