INDEX

Explanations

names and proper nouns, particularly those of notable individuals and places

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

-0.15

bed

-0.15

 commands

-0.15

 uninstall

-0.14

 critical

-0.14

aff

-0.14

nh

-0.14

Hv

-0.14

URT

-0.14

 company

-0.14

POSITIVE LOGITS

LOCKS

0.18

Äįan

0.17

ãģģ

0.17

á»ĭp

0.16

dda

0.16

[top

0.15

Å¼e

0.15

fty

0.15

oundary

0.15

 RoundedRectangle

0.15

Activations Density 0.135%

names and proper nouns, particularly those of notable individuals and places

No Comments

No Known Activations