INDEX

Explanations

references to structured data or database queries

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

unting

-0.16

 Invent

-0.15

ether

-0.15

ethoven

-0.15

lass

-0.15

iesz

-0.14

nummer

-0.14

ais

-0.14

acer

-0.14

 leash

-0.14

POSITIVE LOGITS

iline

0.15

orama

0.15

Ī¬

0.15

arus

0.15

olen

0.15

ÃĹ↵↵

0.14

CursorPosition

0.14

avax

0.14

Fla

0.14

Kv

0.13

Activations Density 0.150%

references to structured data or database queries

No Comments

No Known Activations