INDEX

Explanations

references to brevity and clarity in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

rg

-0.15

Ãło

-0.15

kia

-0.15

pip

-0.15

jak

-0.15

fer

-0.14

Fer

-0.14

pip

-0.14

rio

-0.14

POSITIVE LOGITS

WORDS

0.18

à¥įà¤¥à¤¨

0.16

 words

0.16

ControlEvents

0.16

.glide

0.15

VOICE

0.15

voice

0.15

words

0.15

 à¹Ĩ

0.14

Ð¦Ðµ

0.14

Activations Density 0.085%

references to brevity and clarity in communication

No Comments

No Known Activations