INDEX

Explanations

specific character names and their corresponding roles in film and television narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Argb

-0.15

illus

-0.14

bourne

-0.14

áº©n

-0.13

áº©m

-0.13

abez

-0.13

assen

-0.13

ÑīÐ¸Ðº

-0.13

ility

-0.13

Ð°ÑĢÑħ

-0.13

POSITIVE LOGITS

ovsky

0.15

 animation

0.14

Ð²Ð¸ÑĩÐ°Ð¹

0.14

Ð»Ð°Ð´Ð¸

0.14

breaker

0.14

 Archives

0.14

Ð»ÑĸÑĤ

0.13

 Ø¨ÙĨØ¯ÛĮ

0.13

amic

0.13

_TypeDef

0.13

Activations Density 0.017%

specific character names and their corresponding roles in film and television narratives

No Comments

No Known Activations