INDEX

Explanations

coding functions related to object and array manipulation

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

fern

-0.16

attice

-0.16

strup

-0.16

.randomUUID

-0.14

ãĥ³ãĥĩ

-0.14

 æ¼

-0.14

èµı

-0.14

 Baths

-0.14

auf

-0.14

auen

-0.14

POSITIVE LOGITS

omatic

0.14

hel

0.14

Hoe

0.14

ivos

0.13

paque

0.13

æ¬ł

0.13

(éĩĳ

0.13

Activations Density 0.298%

coding functions related to object and array manipulation

No Comments

No Known Activations