INDEX

Explanations

references to specific movies and their notable elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Doll

-0.15

 addCriterion

-0.15

sko

-0.14

 Kraj

-0.14

 Simon

-0.14

 administr

-0.13

 cest

-0.13

strcasecmp

-0.13

inally

-0.13

POSITIVE LOGITS

 Pirates

0.22

 Heard

0.21

 Actor

0.16

 Amber

0.15

 Fairfax

0.15

JK

0.15

 Actress

0.15

olib

0.15

 Johnny

0.15

Johnny

0.15

Activations Density 0.005%

references to specific movies and their notable elements

No Comments

No Known Activations