INDEX

Explanations

phrases highlighting comparisons and variations in circumstances or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 apart

-0.17

roy

-0.16

chen

-0.15

PK

-0.15

ohn

-0.14

pler

-0.14

inx

-0.14

 Apart

-0.14

atty

-0.14

POSITIVE LOGITS

ibase

0.15

Lua

0.15

lient

0.14

itudes

0.14

ulla

0.14

ilk

0.14

:UITableView

0.14

Ú¯Ùĩ

0.14

ãĥ¼ãĤ¿ãĥ¼

0.13

utta

0.13

Activations Density 0.858%

phrases highlighting comparisons and variations in circumstances or behaviors

No Comments

No Known Activations