INDEX

Explanations

references to programming constructs and functions related to DOM manipulation and event handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

_traits

-0.14

 Maul

-0.14

 ring

-0.14

²

-0.14

-0.13

usan

-0.13

ow

-0.13

 Electoral

-0.13

POSITIVE LOGITS

htable

0.16

dex

0.15

gÄ±n

0.15

izin

0.14

illez

0.14

echa

0.14

 Birch

0.14

/list

0.14

hir

0.13

ivr

0.13

Activations Density 0.218%

references to programming constructs and functions related to DOM manipulation and event handling

No Comments

No Known Activations