INDEX

Explanations

mentions of competitive outcomes or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uos

-0.16

ono

-0.16

verture

-0.16

aal

-0.15

 Prec

-0.14

_DAC

-0.14

lung

-0.13

Ð¾ÑģÐ»Ð°Ð²

-0.13

Ĭ

-0.13

Ð°Ð»Ð¾Ð²

-0.13

POSITIVE LOGITS

eyse

0.15

 uzavÅĻ

0.14

soon

0.14

":""

0.14

aban

0.14

nds

0.13

ä¹Ĺ

0.13

Sig

0.13

Jah

0.13

ÅŁk

0.13

Activations Density 0.041%

mentions of competitive outcomes or events

No Comments

No Known Activations