INDEX

Explanations

names of people or characters in 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 @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

elen

-0.18

alen

-0.17

 Crosby

-0.17

craper

-0.15

el

-0.15

 Lancaster

-0.14

LM

-0.14

èĩ

-0.14

zman

-0.14

Į

-0.14

POSITIVE LOGITS

 Gill

0.59

 Jill

0.52

oll

0.52

 Holl

0.52

OLL

0.50

 Pell

0.49

ill

0.46

ELL

0.45

ull

0.45

pill

0.44

Activations Density 0.126%

names of people or characters in various contexts

No Comments

No Known Activations