INDEX

Explanations

phrases relating to accidental actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ilm

-0.18

loo

-0.16

ALLOC

-0.14

rani

-0.14

 ridge

-0.13

ao

-0.13

ibre

-0.13

PB

-0.13

hora

-0.12

POSITIVE LOGITS

uby

0.19

omas

0.16

ayd

0.16

aneously

0.15

aneous

0.15

rete

0.14

ably

0.14

avig

0.14

çĦ¶

0.14

ously

0.14

Activations Density 0.013%

phrases relating to accidental actions or events

No Comments

No Known Activations