INDEX

Explanations

mentions of specific episodes and related events in a series or franchise context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

reau

-0.12

Å¡k

-0.12

ÌĨ

-0.12

ylland

-0.12

ìľłë¨¸

-0.11

Ð¾Ð¿Ð¾Ð»

-0.11

ãĤĤãģ£ãģ¨

-0.11

averse

-0.11

reon

-0.11

erif

-0.11

POSITIVE LOGITS

Question

0.14

 [âĢ¦

0.14

Âłt

0.13

Ð¾ÑĢÐ°Ñı

0.13

ÂłH

0.12

ÂłN

0.12

 ÃĤ

0.11

Âłin

0.11

(QIcon

0.11

/xhtml

0.11

Activations Density 7.419%

mentions of specific episodes and related events in a series or franchise context

No Comments

No Known Activations