INDEX

Explanations

numerical values and version identifiers

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

PROTO

-0.16

Ð¼Ð¾ÑĢ

-0.15

 Ø§Ø«

-0.15

ksen

-0.15

ESA

-0.15

-placeholder

-0.15

agens

-0.14

pone

-0.14

apsed

-0.13

lop

-0.13

POSITIVE LOGITS

é¡¿

0.15

ugs

0.14

 bind

0.14

ÃŃÅ¾

0.14

rot

0.14

immune

0.14

ryo

0.14

Mem

0.14

unar

0.13

Activations Density 0.015%

numerical values and version identifiers

No Comments

No Known Activations