INDEX

Explanations

statements and claims from insiders or sources about sensitive information related to security issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Niet

-0.15

rightness

-0.15

legen

-0.15

ÑģÑĤÐ²ÐµÐ½Ð½Ð¾

-0.14

impan

-0.13

udget

-0.13

alam

-0.13

 Stocks

-0.13

agne

-0.13

Î¿ÏħÏĤ

-0.13

POSITIVE LOGITS

Ø±ÙĪØª

0.16

bach

0.14

LTR

0.14

 gubern

0.14

ffa

0.14

_handling

0.13

à¥įà¤·à¤£

0.13

erin

0.13

lul

0.13

æľį

0.13

Activations Density 0.044%

statements and claims from insiders or sources about sensitive information related to security issues

No Comments

No Known Activations