INDEX

Explanations

repeated phrases indicating conditions or causes in statements

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

dag

-0.16

ÑģÐ°Ð¼

-0.15

oose

-0.15

ãģĬ

-0.15

 Independence

-0.14

Independ

-0.14

arnation

-0.14

erc

-0.14

abis

-0.14

uya

-0.14

POSITIVE LOGITS

pector

0.20

Ð³Ð¾ÑĤ

0.17

inea

0.16

opr

0.15

uptools

0.14

uka

0.14

iky

0.14

ãĥ©ãĥĥãĤ¯

0.14

cher

0.14

 Lean

0.14

Activations Density 0.140%

repeated phrases indicating conditions or causes in statements

No Comments

No Known Activations