INDEX

Explanations

words related to roasting or cooking processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.16

orient

-0.14

ÛĮØ²ÛĮ

-0.14

tul

-0.13

ÏĥÎµÎ¹ÏĤ

-0.13

OM

-0.13

nerg

-0.13

uries

-0.13

rowable

-0.13

POSITIVE LOGITS

ihn

0.16

elly

0.15

antan

0.15

ìį¨

0.15

idges

0.14

DonaldTrump

0.14

ply

0.14

inet

0.14

iap

0.14

Äįin

0.14

Activations Density 0.011%

words related to roasting or cooking processes

No Comments

No Known Activations