INDEX

Explanations

references to programming and coding languages or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 ÑħÐ²

-0.16

lys

-0.16

ilerden

-0.16

fat

-0.15

iker

-0.15

uppy

-0.15

uo

-0.14

ively

-0.14

ROID

-0.14

æĶ¿

-0.14

POSITIVE LOGITS

olle

0.15

wil

0.15

 Ø§Ø«

0.15

curity

0.15

à¸«à¸¡

0.15

 Patt

0.14

Uns

0.14

olis

0.14

 gerek

0.14

ogg

0.14

Activations Density 0.010%

references to programming and coding languages or concepts

No Comments

No Known Activations