INDEX

Explanations

variations of the word "ke."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ler

-0.16

ness

-0.15

shire

-0.15

lias

-0.15

Î´Î·

-0.14

roi

-0.14

ãĥ£

-0.14

avec

-0.14

ERC

-0.13

 hint

-0.13

POSITIVE LOGITS

adol

0.16

adden

0.16

inject

0.15

 Ridley

0.15

inn

0.15

elow

0.15

StateManager

0.14

haul

0.14

ancode

0.14

eo

0.14

Activations Density 0.014%

variations of the word "ke."

No Comments

No Known Activations

variations of the word "ke."

No Comments

No Known Activations