INDEX

Explanations

references to various stages and phases of development or planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

lox

-0.13

upported

-0.13

USIC

-0.13

 ÑģÐ¿ÑĢÐ°Ð²Ð¸

-0.13

outers

-0.12

Ð¾ÑĤÐ°

-0.11

à¹ģà¸£à¸ĩ

-0.11

imony

-0.11

OCUS

-0.11

GFX

-0.11

POSITIVE LOGITS

 stage

0.92

 stages

0.88

 phase

0.81

 phases

0.76

stage

0.75

 Stage

0.70

-stage

0.68

phase

0.65

Stage

0.63

éĺ¶æ®µ

0.62

Activations Density 0.169%

references to various stages and phases of development or planning

No Comments

No Known Activations