INDEX

Explanations

frequent articles and prepositions in textual content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 Forgotten

-0.17

afe

-0.14

Continue

-0.14

 confidential

-0.14

Kab

-0.14

 Bett

-0.13

 caps

-0.13

 forgotten

-0.13

avern

-0.13

POSITIVE LOGITS

 peÅŁ

0.17

quia

0.15

ensa

0.14

ÏģÎ¯

0.14

rez

0.14

 ç¨

0.14

_ioctl

0.14

AYOUT

0.14

rede

0.14

 Minor

0.13

Activations Density 0.001%

frequent articles and prepositions in textual content

No Comments

No Known Activations