INDEX

Explanations

phrases that convey actions or directives involving "get."

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

azo

-0.17

reon

-0.15

entine

-0.15

SEC

-0.15

andalone

-0.15

obel

-0.15

 Ð¿ÑĢÐ¾Ð³

-0.15

esan

-0.14

vard

-0.14

POSITIVE LOGITS

Gri

0.15

 ìĨ

0.14

 sympt

0.14

ÐµÑĢÐ²

0.14

igital

0.14

erv

0.14

inson

0.14

Ã¼zel

0.13

igham

0.13

<quote

0.13

Activations Density 0.058%

phrases that convey actions or directives involving "get."

No Comments

No Known Activations