INDEX

Explanations

references to specific measurements or quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

edin

-0.16

king

-0.15

up

-0.15

aad

-0.14

iri

-0.14

 fron

-0.14

uen

-0.14

ney

-0.14

oga

-0.14

æŃ

-0.13

POSITIVE LOGITS

tsky

0.17

.).↵↵

0.16

0.15

.Ð¡

0.15

SetBranch

0.15

 HOLDERS

0.15

fsp

0.15

elter

0.15

.:.

0.15

ICLE

0.15

Activations Density 0.268%

references to specific measurements or quantities

No Comments

No Known Activations