INDEX

Explanations

the word "know" and its variations, indicating a focus on knowledge or awareness

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

illery

-0.16

aven

-0.15

iae

-0.15

inal

-0.15

 dispatch

-0.14

'gc

-0.14

unate

-0.14

way

-0.14

 conven

-0.14

Thr

-0.14

POSITIVE LOGITS

velle

0.16

assis

0.16

adh

0.15

ey

0.14

atch

0.14

oyo

0.14

stead

0.14

etchup

0.14

getConnection

0.14

isay

0.14

Activations Density 0.019%

the word "know" and its variations, indicating a focus on knowledge or awareness

No Comments

No Known Activations