INDEX

Explanations

references to significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

obre

-0.17

igli

-0.15

rella

-0.15

 uphill

-0.14

aub

-0.14

udent

-0.14

ald

-0.13

ibase

-0.13

ritel

-0.13

avig

-0.13

POSITIVE LOGITS

ipt

0.17

VERTISE

0.15

suffix

0.15

swire

0.15

raÅ¾

0.15

ABCDEFGHIJKLMNOP

0.14

 Bomb

0.14

_endian

0.14

Ľ°

0.13

ãĤĬãģ¨

0.13

Activations Density 0.038%

references to significant events or milestones

No Comments

No Known Activations