INDEX

Explanations

recipes or cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

igation

-0.16

adla

-0.16

ÙħÙĨ

-0.16

imus

-0.15

.scalablytyped

-0.15

pic

-0.15

_NOP

-0.15

oleÄį

-0.15

hang

-0.15

boro

-0.15

POSITIVE LOGITS

 base

0.17

 vodka

0.17

.Generated

0.17

 Base

0.15

 Fleet

0.15

 Fresh

0.15

Framework

0.14

 thaw

0.14

 Blitz

0.14

 Framework

0.14

Activations Density 0.077%

recipes or cooking instructions

No Comments

No Known Activations