INDEX

Explanations

references to models and structures related to art and education

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ampp

-0.18

ppo

-0.16

_rng

-0.16

chw

-0.16

ezi

-0.15

ÎµÎ¹Î¿

-0.15

 mainland

-0.14

Enumerator

-0.14

ÑĸÑģÐ½Ð¾

-0.14

vang

-0.14

POSITIVE LOGITS

 models

0.16

 representations

0.16

 representation

0.15

zee

0.15

roc

0.15

 Bits

0.15

LEM

0.14

 getModel

0.14

ures

0.14

.bits

0.14

Activations Density 0.090%

references to models and structures related to art and education

No Comments

No Known Activations