INDEX

Explanations

references to film characters and their roles in narratives

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

uter

-0.16

ãĥ¼ãĥį

-0.15

ez

-0.15

cmds

-0.15

 evaluation

-0.14

jmp

-0.14

jc

-0.14

hab

-0.14

ced

-0.14

ande

-0.14

POSITIVE LOGITS

Bat

0.35

 Gotham

0.31

Bat

0.31

 Batman

0.31

BAT

0.30

bat

0.29

Batman

0.28

bat

0.28

BAT

0.28

 bats

0.26

Activations Density 0.049%

references to film characters and their roles in narratives

No Comments

No Known Activations