INDEX

Explanations

instances of the word "look" and its variations

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

ingleton

-0.16

iye

-0.15

ugh

-0.15

wet

-0.14

stk

-0.14

wr

-0.14

igli

-0.14

íĤ¬

-0.13

akah

-0.13

 wykon

-0.13

POSITIVE LOGITS

CMS

0.15

heim

0.15

tern

0.15

SCRI

0.14

Ð¿ÑĢÐ°Ð²

0.14

lotte

0.14

ãģ¾ãģ¾

0.14

IRST

0.14

ifornia

0.14

ERN

0.14

Activations Density 0.054%

instances of the word "look" and its variations

No Comments

No Known Activations