INDEX

Explanations

references to Australian films and related cinematic topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Scene

-0.17

 scene

-0.17

ancell

-0.16

 Scene

-0.16

REA

-0.16

ertools

-0.15

ettes

-0.15

_scene

-0.15

 animator

-0.15

omen

-0.15

POSITIVE LOGITS

 buddy

0.18

 tale

0.18

coming

0.17

 film

0.17

 prestige

0.17

 ensemble

0.17

heimer

0.16

ehr

0.16

dr

0.16

spy

0.16

Activations Density 0.158%

references to Australian films and related cinematic topics

No Comments

No Known Activations