INDEX

Explanations

phrases indicating location or presence within a space

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

unos

-0.15

essler

-0.13

pit

-0.13

vise

-0.13

pretty

-0.13

ToObject

-0.13

STA

-0.13

Î¼ÎŃ

-0.13

UDO

-0.12

eut

-0.12

POSITIVE LOGITS

éľ²

0.15

ffer

0.13

íĺ¼

0.13

InParameter

0.13

iates

0.13

-sex

0.13

å¯¸

0.13

enance

0.13

ÑĢÐ°Ð²Ð¸

0.13

 Kens

0.13

Activations Density 0.235%

phrases indicating location or presence within a space

No Comments

No Known Activations