INDEX

Explanations

identifiers and references to security vulnerabilities

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

aste

-0.19

NotSupportedException

-0.16

isque

-0.16

elib

-0.16

.timedelta

-0.15

çĽĳåĲ¬é¡µéĿ¢

-0.15

iola

-0.14

ascar

-0.14

_Tis

-0.14

chg

-0.14

POSITIVE LOGITS

0.15

 evenly

0.14

Sie

0.14

 resist

0.14

oi

0.14

 Spar

0.14

wa

0.13

_RESP

0.13

 resistance

0.13

 excess

0.13

Activations Density 0.015%

identifiers and references to security vulnerabilities

No Comments

No Known Activations