INDEX

Explanations

terms related to flagship products or stores

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

fsp

-0.15

ãģ£ãģ¡

-0.15

 Dream

-0.14

 tame

-0.14

geist

-0.14

 Lever

-0.14

egasus

-0.14

addir

-0.13

icle

-0.13

stad

-0.13

POSITIVE LOGITS

apult

0.16

rit

0.15

mast

0.14

ÐµÐºÐ°ÑĢ

0.14

 ÙģØ§Ø±

0.14

alah

0.13

INTR

0.13

Ð»Ð°Ð³Ð¾Ð´

0.13

à¸°

0.13

Fall

0.13

Activations Density 0.001%

terms related to flagship products or stores

No Comments

No Known Activations