INDEX

Explanations

expressions related to collaboration and teamwork

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ars

-0.15

endon

-0.14

osto

-0.14

 há»Ļ

-0.14

uce

-0.14

ruc

-0.14

avia

-0.14

unist

-0.13

uur

-0.13

sched

-0.13

POSITIVE LOGITS

owski

0.17

conds

0.16

roid

0.16

ØªØ²

0.15

nds

0.14

ingga

0.14

ÑĩÐ¸ÑģÐ»

0.14

andro

0.14

 Conc

0.14

adr

0.14

Activations Density 0.260%

expressions related to collaboration and teamwork

No Comments

No Known Activations