INDEX

Explanations

timestamps and update annotations related to articles

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

ucci

-0.15

éľ²

-0.15

Ð½Ð¾Ð¿

-0.15

ozor

-0.14

 ApiException

-0.14

umont

-0.14

iese

-0.14

inely

-0.13

Ð³Ð»

-0.13

pedia

-0.13

POSITIVE LOGITS

 splice

0.15

erral

0.15

ìĦł

0.15

Ð²Ð¾Ð´

0.15

ìĿ´ìĸ´

0.15

ç£¨

0.15

ï»¿#

0.14

 cabo

0.14

reb

0.13

roach

0.13

Activations Density 0.010%

timestamps and update annotations related to articles

No Comments

No Known Activations