INDEX

Explanations

references to alumni and alumni associations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ape

-0.19

chter

-0.17

lington

-0.16

 Gerr

-0.15

Gly

-0.14

ger

-0.14

apas

-0.14

Ã³b

-0.14

fried

-0.14

iar

-0.14

POSITIVE LOGITS

sie

0.15

outh

0.15

uzzi

0.15

Ð°ÑĤÐºÐ¾Ð²

0.15

IMO

0.14

ê¸ī

0.14

atic

0.14

ktop

0.14

tep

0.14

 Nurs

0.13

Activations Density 0.006%

references to alumni and alumni associations

No Comments

No Known Activations