INDEX

Explanations

references to lunch and meal breaks

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

.nc

-0.16

opoulos

-0.16

eve

-0.15

ucher

-0.15

ohn

-0.15

 upper

-0.14

pur

-0.14

 Sheets

-0.14

laÄį

-0.14

lay

-0.13

POSITIVE LOGITS

eting

0.17

vale

0.15

time

0.15

break

0.14

lik

0.14

MOTE

0.14

atori

0.14

.getItemId

0.13

azar

0.13

ificent

0.13

Activations Density 0.015%

references to lunch and meal breaks

No Comments

No Known Activations