INDEX

Explanations

instances of character names and their corresponding actions or emotional states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

lesen

-0.17

 fort

-0.15

Å¾il

-0.15

Ø·Ø§ÙĦ

-0.14

lexport

-0.14

avigate

-0.14

aÅŁ

-0.14

loor

-0.14

Å¡ti

-0.14

Äı

-0.14

POSITIVE LOGITS

stÃ¥

0.16

 seins

0.15

holm

0.14

 naÃ¯

0.14

IGH

0.13

ricks

0.13

 absence

0.13

arry

0.13

rick

0.13

Activations Density 0.004%

instances of character names and their corresponding actions or emotional states

No Comments

No Known Activations