INDEX

Explanations

terms related to various types of injuries and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

anness

-0.16

_ary

-0.15

oria

-0.15

amente

-0.14

 anomal

-0.14

arin

-0.14

isk

-0.14

BER

-0.14

roc

-0.14

ropa

-0.13

POSITIVE LOGITS

å®³

0.22

oise

0.16

ive

0.15

ìĥĿ

0.15

/dis

0.15

overy

0.14

lijke

0.14

elog

0.14

ables

0.14

 sustained

0.14

Activations Density 0.024%

terms related to various types of injuries and their implications

No Comments

No Known Activations