INDEX

Explanations

mentions of the word "Lin" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Î¼Î²

-0.17

LES

-0.16

cz

-0.15

 Grim

-0.15

-0.14

eso

-0.14

eller

-0.14

gies

-0.14

ListOf

-0.14

naments

-0.14

POSITIVE LOGITS

coln

0.38

seed

0.28

thic

0.23

nea

0.23

ole

0.22

acre

0.22

agli

0.21

otype

0.21

col

0.21

COL

0.20

Activations Density 0.010%

mentions of the word "Lin" and its variations in various contexts

No Comments

No Known Activations