INDEX

Explanations

technical terms related to databases and programming methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

.habbo

-0.13

iaux

-0.12

reau

-0.12

#af

-0.11

nette

-0.11

dda

-0.11

immel

-0.11

kovi

-0.11

gebn

-0.11

ddit

-0.11

POSITIVE LOGITS

 putas

0.13

 [âĢ¦

0.13

 rá»«ng

0.13

ANJI

0.12

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

0.12

 predecess

0.12

 prostitutas

0.12

 “âĢ¦

0.11

âĢ¦↵

0.11

REW

0.11

Activations Density 10.513%

technical terms related to databases and programming methods

No Comments

No Known Activations