INDEX

Explanations

references to components or parts of systems or entities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

tparam

-0.16

onders

-0.15

ROUT

-0.15

urers

-0.14

inkle

-0.14

our

-0.14

labs

-0.14

PC

-0.14

 Lamb

-0.14

 Franc

-0.14

POSITIVE LOGITS

qml

0.15

aÄĩ

0.15

 háº¡ng

0.14

ylon

0.14

ATALOG

0.14

ocs

0.14

ãĨ

0.14

atri

0.14

yny

0.13

Activations Density 0.012%

references to components or parts of systems or entities

No Comments

No Known Activations