INDEX

Explanations

names of notable individuals, particularly in the context of celebrity and entertainment

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

arde

-0.19

ship

-0.16

ÂŃi

-0.15

aci

-0.14

amb

-0.14

abler

-0.14

æĸ¹

-0.14

Mic

-0.14

raith

-0.14

Ã©ric

-0.14

POSITIVE LOGITS

Pam

0.16

filesystem

0.15

éł¼

0.14

Ð°Ð¼ÐµÑĤ

0.14

.Suppress

0.14

iets

0.14

 Evet

0.13

Ú¯Ø±ÛĮ

0.13

pong

0.13

Activations Density 0.269%

names of notable individuals, particularly in the context of celebrity and entertainment

No Comments

No Known Activations