INDEX

Explanations

instances of the verb "look" and related actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

(iOS

-0.15

 Horny

-0.15

hek

-0.15

&type

-0.14

dra

-0.14

Ãļ

-0.14

raig

-0.14

bjerg

-0.14

deaux

-0.14

IIC

-0.14

POSITIVE LOGITS

eld

0.17

iet

0.15

 Ramp

0.15

wide

0.14

Amb

0.14

Ø§ÙĨÙĩ

0.14

Aut

0.14

dit

0.13

 impl

0.13

Activations Density 0.000%

instances of the verb "look" and related actions

No Comments

No Known Activations