INDEX

Explanations

references to competitive events and match outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

umd

-0.15

indo

-0.15

etes

-0.14

_Offset

-0.14

Ø¬Ùħ

-0.14

 Ð¿ÑĢÐ¾Ð±

-0.13

 ØŃØ¬Ùħ

-0.13

 forg

-0.13

eter

-0.13

 Celt

-0.13

POSITIVE LOGITS

 tÃ©

0.16

borg

0.16

ynes

0.15

 addCriterion

0.14

arus

0.14

::-

0.13

íķĳ

0.13

eming

0.13

 Thur

0.13

Activations Density 0.028%

references to competitive events and match outcomes

No Comments

No Known Activations