INDEX

Explanations

phrases related to providing information and awareness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enger

-0.15

itz

-0.15

terms

-0.14

bic

-0.14

ogi

-0.14

ãģ°

-0.14

infeld

-0.14

otic

-0.14

term

-0.14

ÐµÑĢÐ¶Ð°Ð²

-0.14

POSITIVE LOGITS

indow

0.15

.nextDouble

0.14

xes

0.14

Ø±Ùĥ

0.14

ModelProperty

0.14

à¹Ģà¸ķ

0.14

(*)(

0.13

ounter

0.13

achen

0.13

agraph

0.13

Activations Density 0.016%

phrases related to providing information and awareness

No Comments

No Known Activations