INDEX

Explanations

references to in-house or on-site facilities or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

sian

-0.15

CHANT

-0.15

odore

-0.14

akis

-0.14

 uÄŁ

-0.14

å»³

-0.14

íĥķ

-0.13

typed

-0.13

ammer

-0.13

/Images

-0.13

POSITIVE LOGITS

/off

0.19

/out

0.18

/on

0.18

 resident

0.16

iment

0.15

/internal

0.15

/native

0.15

emble

0.14

util

0.14

FIX

0.14

Activations Density 0.042%

references to in-house or on-site facilities or services

No Comments

No Known Activations