INDEX

Explanations

terms related to various degrees of murder and violent crimes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.jupiter

-0.17

 odense

-0.16

 STRICT

-0.15

evin

-0.15

.pivot

-0.14

riba

-0.14

¶Į

-0.14

 aalborg

-0.14

æĻ®

-0.14

eyse

-0.14

POSITIVE LOGITS

0.15

 Class

0.15

aret

0.15

phyl

0.14

FN

0.14

empl

0.14

_mpi

0.14

Activations Density 0.004%

terms related to various degrees of murder and violent crimes

No Comments

No Known Activations