INDEX

Explanations

specific numeric values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

asio

-0.19

chor

-0.15

oning

-0.15

 Anim

-0.14

anco

-0.14

 cresc

-0.14

 Poke

-0.14

 center

-0.14

iable

-0.14

spin

-0.14

POSITIVE LOGITS

 EntryPoint

0.16

alli

0.15

uali

0.15

ifes

0.15

uxt

0.14

ÏĦÎ¬

0.14

QUE

0.14

riter

0.14

elop

0.14

oice

0.13

Activations Density 0.018%

specific numeric values or measurements

No Comments

No Known Activations