INDEX

Explanations

technical terms and identifiers related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

adena

-0.16

ritel

-0.16

ledi

-0.15

deme

-0.15

 ÙħØ¤Ø³

-0.14

Ø¹Øª

-0.14

 DeÄŁ

-0.14

oÅĪ

-0.14

,strlen

-0.14

ystone

-0.14

POSITIVE LOGITS

ll

0.16

agma

0.15

ful

0.15

 Soros

0.15

etr

0.14

ampa

0.14

aha

0.14

onom

0.14

ifle

0.14

Activations Density 0.179%

technical terms and identifiers related to programming and data structures

No Comments

No Known Activations