INDEX

Explanations

mentions of aid or support, particularly in the context of communities and healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rik

-0.15

.flink

-0.14

hed

-0.14

>tag

-0.14

äº¤

-0.14

quet

-0.14

mana

-0.14

alus

-0.13

ushima

-0.13

crest

-0.13

POSITIVE LOGITS

fit

0.18

 tailor

0.17

 account

0.17

 Tail

0.17

 dedicate

0.16

Ø¹Ø¯Ø§Ø¯

0.16

fits

0.16

 rises

0.16

 rise

0.16

 train

0.16

Activations Density 0.009%

mentions of aid or support, particularly in the context of communities and healthcare

No Comments

No Known Activations