INDEX

Explanations

references to memory and nostalgia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

opak

-0.17

esso

-0.15

WARE

-0.15

çŃĴ

-0.15

ween

-0.15

bstract

-0.14

Ð¾Ð²Ð°ÑĢÐ¸

-0.14

issen

-0.14

ocu

-0.14

stanov

-0.14

POSITIVE LOGITS

ÙĬÙĩ

0.17

WAYS

0.15

ways

0.14

 Exchange

0.14

ives

0.14

rog

0.14

ega

0.14

WAY

0.13

 Scene

0.13

way

0.13

Activations Density 0.116%

references to memory and nostalgia

No Comments

No Known Activations