INDEX

Explanations

terms related to technical concepts and specific domain terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

EEE

-0.15

Moy

-0.15

 Parker

-0.14

agn

-0.14

ru

-0.14

EMA

-0.14

inea

-0.14

onica

-0.14

issen

-0.13

åľ¨çº¿è§Ĥçľĭ

-0.13

POSITIVE LOGITS

 analogy

0.18

 similarly

0.17

 váºŃy

0.17

 ÑģÑħÐ¾Ð´

0.16

Similarly

0.14

Ð²ÑģÑı

0.14

ignon

0.14

dyby

0.14

ungi

0.14

 Similarly

0.14

Activations Density 0.189%

terms related to technical concepts and specific domain terminologies

No Comments

No Known Activations