INDEX

Explanations

expressions of enjoyment or satisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/do

-0.15

ness

-0.15

vars

-0.14

NESS

-0.14

resh

-0.14

arse

-0.14

agem

-0.14

var

-0.14

space

-0.14

inion

-0.13

POSITIVE LOGITS

 Braun

0.17

 disag

0.16

-regexp

0.15

Ð¾ÑĢÑĸÐ²

0.15

anter

0.15

æ¿

0.15

alnÄ±z

0.14

 Rolled

0.14

å¤§åĪ©

0.14

folio

0.14

Activations Density 0.005%

expressions of enjoyment or satisfaction

No Comments

No Known Activations