INDEX

Explanations

references to ratings and assessments of films or shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

oup

-0.17

agen

-0.15

QRST

-0.14

lig

-0.14

 Scal

-0.14

ALAR

-0.14

 Victor

-0.14

 stacked

-0.14

cef

-0.14

odo

-0.14

POSITIVE LOGITS

CLS

0.15

_ASM

0.15

ppard

0.14

raud

0.14

PHPExcel

0.14

inha

0.14

æĹı

0.13

_Lean

0.13

ogra

0.13

/*č↵

0.13

Activations Density 0.053%

references to ratings and assessments of films or shows

No Comments

No Known Activations