INDEX

Explanations

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ernel

-0.14

peg

-0.14

ispecies

-0.14

grab

-0.14

uncated

-0.14

 Rodrig

-0.13

 voksne

-0.13

ixin

-0.13

plier

-0.13

POSITIVE LOGITS

obot

0.15

 Playground

0.15

ensi

0.15

-addons

0.14

 Clare

0.14

iasi

0.14

CANCEL

0.14

wake

0.14

ADATA

0.14

 Irvine

0.14

Activations Density 0.094%

proper nouns and specific names

No Comments

No Known Activations