INDEX

Explanations

phrases that refer to estimates, descriptions, or outlines, particularly in a structured or provisional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

idd

-0.17

ADDE

-0.14

 Noel

-0.14

 ACCESS

-0.13

tera

-0.13

á»Ĳ

-0.13

 brink

-0.13

VRT

-0.13

 Ø¯Ùĩ

-0.13

ActionCreators

-0.13

POSITIVE LOGITS

lak

0.18

 rough

0.17

 Rough

0.16

sk

0.14

rough

0.14

 outline

0.14

lexport

0.14

istor

0.14

anje

0.14

 understanding

0.13

Activations Density 0.162%

phrases that refer to estimates, descriptions, or outlines, particularly in a structured or provisional context

No Comments

No Known Activations