INDEX

Explanations

references to internal structures or concepts related to the body or mind

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

fleet

-0.16

ÎºÎ¹

-0.15

asic

-0.15

roma

-0.14

stered

-0.14

hlen

-0.14

CppClass

-0.14

ergy

-0.14

loom

-0.14

ahl

-0.14

POSITIVE LOGITS

halb

0.19

/out

0.19

/internal

0.17

/Internal

0.16

Core

0.16

most

0.16

-core

0.16

/Core

0.15

 circle

0.15

core

0.15

Activations Density 0.045%

references to internal structures or concepts related to the body or mind

No Comments

No Known Activations