INDEX

Explanations

references to specific films and their elements

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

ofire

-0.17

avern

-0.17

apult

-0.16

viar

-0.16

 epic

-0.15

 offending

-0.15

 Hyper

-0.14

ICAST

-0.14

ugs

-0.14

 saddle

-0.14

POSITIVE LOGITS

 thriller

0.18

asons

0.17

 Hitch

0.16

psz

0.16

 Bates

0.16

 spir

0.15

 spiral

0.15

 puzzles

0.15

abyrinth

0.15

 psychological

0.15

Activations Density 0.145%

references to specific films and their elements

No Comments

No Known Activations