INDEX

Explanations

references to "motion" 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ish

-0.20

ied

-0.18

ash

-0.15

assen

-0.15

yr

-0.15

VERTISEMENT

-0.14

/stdc

-0.14

rish

-0.14

pline

-0.14

heck

-0.14

POSITIVE LOGITS

-picture

0.29

 picture

0.27

 Picture

0.27

Picture

0.23

picture

0.23

 sickness

0.23

less

0.21

_picture

0.21

ality

0.20

 pictures

0.20

Activations Density 0.012%

references to "motion" in various contexts

No Comments

No Known Activations