INDEX

Explanations

words related to strategies or mechanisms for managing resources or information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

poÄįet

-0.17

fov

-0.17

 Borough

-0.15

reak

-0.14

arel

-0.14

Ð±Ð°Ð²

-0.14

 textu

-0.14

abus

-0.14

antt

-0.13

lauf

-0.13

POSITIVE LOGITS

orraine

0.16

stk

0.14

.ErrorCode

0.14

stan

0.14

Î³Î¿Ïģ

0.14

 Butter

0.14

 expiresIn

0.13

 irre

0.13

icast

0.13

.Async

0.13

Activations Density 0.020%

words related to strategies or mechanisms for managing resources or information

No Comments

No Known Activations