INDEX

Explanations

terms related to preliminary or provisional assessments and analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

immel

-0.15

/tcp

-0.14

alian

-0.14

eses

-0.13

ugin

-0.13

 Ð¿ÑĢÐ¸Ð²ÐµÑģÑĤÐ¸

-0.13

adian

-0.13

à¥įà¤¥à¤²

-0.13

_FORWARD

-0.13

'icon

-0.13

POSITIVE LOGITS

reck

0.18

-stage

0.18

ÑĪÑĥ

0.15

enko

0.15

imates

0.15

ÑĢÐµÐ¶

0.15

annya

0.15

_atomic

0.14

 stages

0.14

cust

0.14

Activations Density 0.030%

terms related to preliminary or provisional assessments and analyses

No Comments

No Known Activations