INDEX

Explanations

specific names or proper nouns related to individuals or characters

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

ortal

-0.16

 maximum

-0.15

 Daly

-0.14

 Payne

-0.14

igg

-0.14

Urban

-0.14

YW

-0.14

eries

-0.14

kus

-0.14

POSITIVE LOGITS

ë¡

0.16

ampo

0.15

ebek

0.15

ÑĢÐµÑĤÑĮ

0.14

iph

0.14

muh

0.14

nth

0.14

edith

0.14

bairro

0.14

bsp

0.14

Activations Density 0.392%

specific names or proper nouns related to individuals or characters

No Comments

No Known Activations