INDEX

Explanations

comparisons between entities or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ampus

-0.14

åıĳåĩº

-0.14

ode

-0.13

recursive

-0.13

istor

-0.13

engin

-0.13

 taps

-0.12

SYS

-0.12

SYS

-0.12

ecute

-0.12

POSITIVE LOGITS

jer

0.17

ancock

0.16

obar

0.15

iesen

0.14

ÏİÎ½

0.14

ajar

0.14

atters

0.14

 Heller

0.13

áºŃp

0.13

quat

0.13

Activations Density 0.010%

comparisons between entities or items

No Comments

No Known Activations