INDEX

Explanations

expressions of gratitude and appreciation for experiences and interactions with others

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

-0.16

Ä¾

-0.15

á»į

-0.14

imli

-0.14

ellow

-0.14

orsk

-0.14

.sess

-0.14

anka

-0.13

afen

-0.13

ongan

-0.13

POSITIVE LOGITS

NY

0.16

Ã¨o

0.14

Porno

0.14

 Brace

0.14

 pars

0.14

Ã¼le

0.13

Î¯Î½

0.13

 hopefully

0.13

bol

0.13

PROTO

0.13

Activations Density 0.003%

expressions of gratitude and appreciation for experiences and interactions with others

No Comments

No Known Activations