INDEX

Explanations

references to resin and its variations or related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

tpl

-0.16

ollo

-0.16

awi

-0.16

legen

-0.16

oka

-0.15

rop

-0.14

 sole

-0.14

 erect

-0.14

agua

-0.14

 exotic

-0.14

POSITIVE LOGITS

.BLL

0.16

ptest

0.15

ä»

0.15

ukt

0.14

nde

0.14

DataTask

0.14

ohan

0.14

-hard

0.14

ìĪł

0.13

>(()

0.13

Activations Density 0.008%

references to resin and its variations or related terms

No Comments

No Known Activations