INDEX

Explanations

text elements that provide descriptions and introductions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

STS

-0.16

ê»

-0.15

leh

-0.14

owler

-0.14

 porad

-0.14

QualifiedName

-0.13

adian

-0.13

GT

-0.13

/stream

-0.13

jmp

-0.13

POSITIVE LOGITS

à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ

0.17

ductor

0.16

 describing

0.16

 offsetof

0.15

enticator

0.15

 breve

0.15

 explanation

0.14

 explaining

0.14

iek

0.14

 Wikip

0.14

Activations Density 0.098%

text elements that provide descriptions and introductions

No Comments

No Known Activations