INDEX

Explanations

acronyms and abbreviations commonly associated with organizations and programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 latter

-0.18

orld

-0.16

ationale

-0.15

bes

-0.14

 Reconstruction

-0.13

starter

-0.13

èĢ¶

-0.13

qui

-0.13

.q

-0.13

iei

-0.13

POSITIVE LOGITS

reland

0.16

rvine

0.15

uffers

0.15

iap

0.14

à¸Ļà¸§à¸Ļ

0.14

uples

0.14

cdecl

0.14

ermint

0.14

ÙħÙĪÙĦ

0.14

ifest

0.14

Activations Density 0.062%

acronyms and abbreviations commonly associated with organizations and programs

No Comments

No Known Activations