INDEX

Explanations

references to New Year's celebrations and specific years associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 Verb

-0.15

Verb

-0.15

ãĤ´ãĥª

-0.14

CanBe

-0.14

pcodes

-0.14

hum

-0.14

Ð²ÐµÑī

-0.14

jde

-0.14

NewLabel

-0.14

 Zend

-0.13

POSITIVE LOGITS

fx

0.15

ve

0.15

afi

0.15

quist

0.14

 persistence

0.14

 Mixed

0.14

Persistent

0.14

ichni

0.14

 McCl

0.14

ansom

0.14

Activations Density 0.014%

references to New Year's celebrations and specific years associated with them

No Comments

No Known Activations