INDEX

Explanations

punctuation marks and certain flow indicators in a narrative context

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

reon

-0.17

CKER

-0.17

.Apis

-0.16

arest

-0.15

ickey

-0.15

styleType

-0.15

agn

-0.14

okit

-0.14

otate

-0.14

ductive

-0.14

POSITIVE LOGITS

è¡£

0.15

uary

0.15

 tá»¥

0.15

Dor

0.14

ÅŁk

0.14

 dá»¥

0.14

 amber

0.14

Ð¾ÑĢÐ¾Ð½

0.13

DSP

0.13

isObject

0.13

Activations Density 0.005%

punctuation marks and certain flow indicators in a narrative context

No Comments

No Known Activations