INDEX

Explanations

various forms of the word "item" or related terms in the context of listings and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

imd

-0.16

 tÃ´

-0.15

anter

-0.15

,eg

-0.15

ÑģÑĸÐ¼

-0.15

nish

-0.14

ADO

-0.14

nej

-0.14

nex

-0.14

unker

-0.14

POSITIVE LOGITS

tons

0.18

0.16

Ìģt

0.16

urm

0.15

 warmer

0.14

Ø±Ùĩ

0.14

rst

0.14

--

0.13

Gib

0.13

alt

0.13

Activations Density 0.007%

various forms of the word "item" or related terms in the context of listings and classifications

No Comments

No Known Activations