INDEX

Explanations

words related to academic or analytical concepts, particularly in philosophy and science

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

ãĤ¦ãĥĪ

-0.15

ÅĻiv

-0.15

-0.14

-scrollbar

-0.13

ãĥ©ãĤ¯

-0.13

Pit

-0.13

 recourse

-0.12

íĻĪ

-0.12

_estimator

-0.12

&action

-0.12

POSITIVE LOGITS

ooke

0.14

ancellable

0.14

utin

0.13

 Ø¬ÙĨØ³ÛĮ

0.13

oriously

0.13

é²ľ

0.13

ì§¸

0.13

orsi

0.13

yntax

0.13

elez

0.13

Activations Density 2.820%

words related to academic or analytical concepts, particularly in philosophy and science

No Comments

No Known Activations