INDEX

Explanations

references to the name "Mike"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

èĩ

-0.16

urally

-0.16

nila

-0.16

igner

-0.15

@js

-0.15

-0.14

wang

-0.14

ibur

-0.14

ManagedObject

-0.14

ê³¨

-0.14

POSITIVE LOGITS

 latter

0.21

lette

0.17

ples

0.15

bial

0.15

ops

0.15

SSION

0.14

rometer

0.14

key

0.14

andel

0.14

angelo

0.14

Activations Density 0.013%

references to the name "Mike"

No Comments

No Known Activations