INDEX

Explanations

occurrences of the article "a" and its variations in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

_nat

-0.18

ye

-0.16

isman

-0.15

.TestTools

-0.15

elt

-0.14

etic

-0.14

isper

-0.14

 Fraction

-0.14

 fractional

-0.14

onical

-0.13

POSITIVE LOGITS

dana

0.17

rane

0.15

iman

0.15

getter

0.15

lotte

0.14

ivant

0.14

 tane

0.14

ãĥĢãĥ¼

0.14

ForRow

0.13

Activations Density 0.220%

occurrences of the article "a" and its variations in context

No Comments

No Known Activations