INDEX

Explanations

references to specific companies, events, or individuals within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

eric

-0.15

izzo

-0.14

Jar

-0.14

ION

-0.14

TOTYPE

-0.13

 Bain

-0.13

gnore

-0.13

 Gran

-0.13

ITT

-0.12

POSITIVE LOGITS

ĶåĽŀ

0.15

ife

0.14

akte

0.14

logged

0.14

Ð¾Ð²ÐµÑĢ

0.13

hort

0.13

lobal

0.13

regnum

0.13

deÅŁ

0.13

rego

0.13

Activations Density 0.166%

references to specific companies, events, or individuals within various contexts

No Comments

No Known Activations