INDEX

Explanations

phrases that indicate actions related to managing, working, or investing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Ø§ÙģØª

-0.15

ncia

-0.15

inke

-0.15

_CI

-0.14

>.↵↵

-0.14

ignet

-0.14

ouce

-0.14

%.↵

-0.14

QUEST

-0.13

>.↵

-0.13

POSITIVE LOGITS

 Breed

0.14

zyst

0.13

abase

0.13

arg

0.13

ibo

0.13

 Kirk

0.13

”:

0.13

”;

0.12

YTE

0.12

apro

0.12

Activations Density 0.232%

phrases that indicate actions related to managing, working, or investing

No Comments

No Known Activations