INDEX

Explanations

occurrences of the name "Mike" 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

nya

-0.16

.googleapis

-0.16

ico

-0.15

mites

-0.15

ipur

-0.15

iert

-0.15

CHO

-0.14

weg

-0.14

mente

-0.14

 âĹĦ

-0.14

POSITIVE LOGITS

 Huckabee

0.19

 Tyson

0.18

 Pence

0.17

itz

0.17

 Bloomberg

0.16

laus

0.15

 latter

0.15

SELL

0.14

WAYS

0.14

cro

0.14

Activations Density 0.009%

occurrences of the name "Mike" in various contexts

No Comments

No Known Activations