INDEX

Explanations

bracketed notations or specific label designations

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

kea

-0.17

ilight

-0.15

 strict

-0.15

etal

-0.15

 desp

-0.15

ziel

-0.14

 Colo

-0.14

chte

-0.14

datum

-0.14

enia

-0.14

POSITIVE LOGITS

.DropTable

0.17

atre

0.17

yem

0.16

çĲ´

0.16

avian

0.14

abcdefghijklmnop

0.14

 kali

0.14

 sami

0.14

æ´²

0.14

_wire

0.14

Activations Density 0.194%

bracketed notations or specific label designations

No Comments

No Known Activations