INDEX

Explanations

phrases related to violent or threatening actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ÐĴÐ¡

-0.15

tel

-0.15

wire

-0.15

PACE

-0.15

 wire

-0.15

ewire

-0.14

Ð»ÑıÐ´

-0.14

nova

-0.14

iple

-0.14

Nova

-0.14

POSITIVE LOGITS

ssel

0.16

JNI

0.16

 Patch

0.15

.patch

0.14

yonel

0.14

 patch

0.14

Nut

0.13

Å¡tÃŃ

0.13

keys

0.13

Activations Density 0.085%

phrases related to violent or threatening actions

No Comments

No Known Activations