INDEX

Explanations

numerical references related to historical data or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

unch

-0.15

æ°ı

-0.14

 Ð¶Ðµ

-0.14

ures

-0.13

engl

-0.13

ATH

-0.13

zilla

-0.13

tein

-0.13

Î´Î¯

-0.13

POSITIVE LOGITS

UTERS

0.16

CLUS

0.15

æĽ´å¤ļ

0.15

Ctrls

0.13

CLUDING

0.13

Ð³Ð»

0.13

uentes

0.13

_fmt

0.13

(formatter

0.13

âĢİ

0.13

Activations Density 0.018%

numerical references related to historical data or events

No Comments

No Known Activations