INDEX

Explanations

HTML comments and related syntax within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

oods

-0.16

ayed

-0.16

itoris

-0.15

zew

-0.15

uther

-0.14

acak

-0.14

uffy

-0.13

utar

-0.13

itta

-0.13

atif

-0.13

POSITIVE LOGITS

CHANT

0.15

alara

0.15

Bog

0.13

IntegerField

0.13

 uncert

0.13

.synthetic

0.13

çĲĨè§£

0.13

 incididunt

0.13

gy

0.13

Activations Density 0.021%

HTML comments and related syntax within code

No Comments

No Known Activations