INDEX

Explanations

names and proper nouns associated with individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aku

-0.16

hle

-0.16

/pm

-0.15

Tul

-0.14

hoff

-0.14

ÏĥÎ¹Î±

-0.14

IRD

-0.14

ipp

-0.14

adesh

-0.14

ique

-0.13

POSITIVE LOGITS

etur

0.15

esModule

0.15

ÙĥØ§Øª

0.14

erli

0.14

iams

0.14

oen

0.14

 Ø§ÙĦØªÙĪ

0.14

transparent

0.14

 haul

0.13

 bÃ¼

0.13

Activations Density 0.034%

names and proper nouns associated with individuals

No Comments

No Known Activations