INDEX

Explanations

film titles and related terminology in various media contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

(disposing

-0.15

oload

-0.15

elez

-0.14

engan

-0.14

 argument

-0.14

Xt

-0.14

omer

-0.13

Ã¹a

-0.13

mb

-0.13

POSITIVE LOGITS

eto

0.15

 Sche

0.15

_guard

0.14

ÑĤÐ¸Ðº

0.14

WithError

0.14

rax

0.14

 fame

0.14

 ÑĤÐ¾Ð²

0.13

integral

0.13

èĪ¬

0.13

Activations Density 0.104%

film titles and related terminology in various media contexts

No Comments

No Known Activations