INDEX

Explanations

specific references to statistics and metrics related to performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÅĻet

-0.14

 veÅĻejnÃ©

-0.14

é§ħå¾ĴæŃ©

-0.14

 zaÄįÃ¡tku

-0.14

.splitContainer

-0.13

 DÃ¼n

-0.13

Å¡ti

-0.13

 kabil

-0.13

ÅĽnie

-0.13

ITTE

-0.13

POSITIVE LOGITS

_{}

0.12

\grid

0.12

#ab

0.11

,ID

0.11

amp

0.11

|array

0.11

 dá»ĭ

0.11

#ac

0.11

utex

0.11

nt

0.10

Activations Density 4.487%

specific references to statistics and metrics related to performance

No Comments

No Known Activations