INDEX

Explanations

words that convey certainty or decisiveness

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

znik

-0.17

ippy

-0.16

erval

-0.15

edian

-0.15

ucht

-0.14

 treasure

-0.14

Î»Îµ

-0.14

 vast

-0.14

eker

-0.14

lero

-0.14

POSITIVE LOGITS

fat

0.16

ilon

0.14

imizer

0.13

Ns

0.13

ÏĤ

0.13

_loop

0.13

çĭĲ

0.13

ouri

0.13

 loops

0.13

atures

0.13

Activations Density 0.016%

words that convey certainty or decisiveness

No Comments

No Known Activations