INDEX

Explanations

concepts or terms related to variety and classification within contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ancement

-0.17

 ÑģÐ¿Ð¾ÑģÐ¾Ð±Ð¾Ð¼

-0.15

 Ð¿Ð¾ÐºÐ¾Ð»

-0.15

sein

-0.14

indre

-0.14

boom

-0.14

à¸ķ

-0.14

 sque

-0.14

POSITIVE LOGITS

loy

0.17

anza

0.16

ÐµÐ½Ð½Ð¾ÑģÑĤÑĮ

0.15

 atmos

0.15

pill

0.15

à¹Ĥà¸Ĭ

0.15

 Provid

0.15

 ÑĥÑĩÐ°ÑģÑĤÑĮ

0.14

subst

0.14

emme

0.14

Activations Density 0.027%

concepts or terms related to variety and classification within contexts

No Comments

No Known Activations