INDEX

Explanations

mentions of numerical data, particularly in relation to durations and counts

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

zz

-0.17

iem

-0.17

liness

-0.16

ings

-0.16

pin

-0.15

ful

-0.15

ispers

-0.15

anos

-0.14

ie

-0.14

aise

-0.14

POSITIVE LOGITS

ityEngine

0.17

ughter

0.15

olland

0.15

enery

0.14

stroy

0.14

sut

0.13

opensource

0.13

PIO

0.13

GLOBALS

0.13

rava

0.13

Activations Density 0.164%

mentions of numerical data, particularly in relation to durations and counts

No Comments

No Known Activations