INDEX

Explanations

references to significant numerical values or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

isible

-0.16

istring

-0.15

Ð¾Ð´Ñĭ

-0.15

éĨ´

-0.15

ols

-0.15

uard

-0.14

orent

-0.14

amera

-0.14

emory

-0.14

ocado

-0.14

POSITIVE LOGITS

antar

0.16

elligence

0.15

_ptrs

0.15

 Blick

0.14

åĲ¾

0.14

 Rodgers

0.14

ugo

0.14

GetX

0.13

INCLUDE

0.13

IRS

0.13

Activations Density 0.027%

references to significant numerical values or measurements

No Comments

No Known Activations