INDEX

Explanations

objects and items relevant to settings or scenes described in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 into

-0.16

ina

-0.16

ernel

-0.15

Occ

-0.15

 exist

-0.15

ispers

-0.14

OTS

-0.14

ä»²

-0.14

ISA

-0.14

POSITIVE LOGITS

 lying

0.33

 Ð»ÐµÐ¶

0.30

Lie

0.25

lay

0.25

Lie

0.24

 laying

0.24

lie

0.24

 laid

0.21

lie

0.21

 lies

0.20

Activations Density 0.243%

objects and items relevant to settings or scenes described in the text

No Comments

No Known Activations