INDEX

Explanations

occurrences of significant events or stages in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

cki

-0.17

pty

-0.16

Ã¥l

-0.15

PTY

-0.15

zg

-0.15

 ÙģØ³

-0.14

adge

-0.14

rong

-0.14

Ð°ÑĤÐµÐ¼

-0.14

rame

-0.14

POSITIVE LOGITS

 ÙħØ¨Ø§Ø´

0.20

wards

0.16

words

0.16

veyor

0.15

Å¥

0.14

 InitializeComponent

0.14

word

0.14

ÑħÐ¸

0.13

NOI

0.13

amon

0.13

Activations Density 0.094%

occurrences of significant events or stages in a narrative context

No Comments

No Known Activations