INDEX

Explanations

references to product issues and customer service interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÑĤÐ°Ð±

-0.16

steady

-0.15

plx

-0.15

ulos

-0.14

cratch

-0.14

uge

-0.14

ÑĦÐµÑĢ

-0.14

hta

-0.14

Decoder

-0.13

à¤§à¤°

-0.13

POSITIVE LOGITS

ipy

0.15

 Tits

0.15

sez

0.15

auty

0.14

elerik

0.14

argar

0.14

ior

0.14

cbc

0.14

rops

0.13

å¯

0.13

Activations Density 0.063%

references to product issues and customer service interactions

No Comments

No Known Activations