INDEX

Explanations

specific technical terms and jargon related to computer science and cybersecurity

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

.pretty

-0.15

LETTE

-0.15

ãĥĥãĤ«ãĥ¼

-0.14

ypes

-0.14

é±

-0.14

cai

-0.14

.cgi

-0.14

å®Ļ

-0.14

phere

-0.14

äºľ

-0.14

POSITIVE LOGITS

isse

0.16

avail

0.15

ÙĭØ§

0.14

argas

0.14

oris

0.14

 lá»¥c

0.14

ãĤ¿ãĤ¤

0.14

 avail

0.14

.Modules

0.13

Ð¾ÑĤÑĥ

0.13

Activations Density 0.290%

specific technical terms and jargon related to computer science and cybersecurity

No Comments

No Known Activations