INDEX

Explanations

references to executions and related violent actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

æĴ

-0.15

 genu

-0.15

ija

-0.15

agara

-0.15

APER

-0.15

 congress

-0.15

yu

-0.14

 stag

-0.14

POSITIVE LOGITS

usercontent

0.16

usp

0.16

.Undef

0.15

_COMPAT

0.14

åĩ

0.14

 knull

0.14

ResultsController

0.14

Ð´ÐµÐºÑģ

0.14

 eskort

0.14

>(()

0.14

Activations Density 0.036%

references to executions and related violent actions

No Comments

No Known Activations