INDEX

Explanations

inquiries about searching for various items or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

omanip

-0.17

adx

-0.15

(es

-0.15

abase

-0.14

 Fits

-0.14

isan

-0.13

 lá»ĩ

-0.13

Äįel

-0.13

subscribe

-0.13

utar

-0.13

POSITIVE LOGITS

ewe

0.16

hled

0.16

 ways

0.15

/search

0.15

 seek

0.15

0.14

 Ways

0.14

çļĦæĺ¯

0.14

ays

0.14

ulis

0.14

Activations Density 0.084%

inquiries about searching for various items or options

No Comments

No Known Activations