INDEX

Explanations

phrases that initiate questions or indicate conditionality

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

iola

-0.15

jang

-0.15

aptive

-0.14

anik

-0.13

nip

-0.13

-generated

-0.13

fish

-0.13

ÏĥÎº

-0.13

$__

-0.13

BX

-0.13

POSITIVE LOGITS

0.15

.openg

0.14

oint

0.14

odox

0.14

 Grund

0.14

imens

0.14

.nasa

0.13

infer

0.13

velle

0.13

ÑĢÐ¸Ð¹

0.13

Activations Density 0.017%

phrases that initiate questions or indicate conditionality

No Comments

No Known Activations