INDEX

Explanations

words associated with social critique and moral accountability

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

ittel

-0.15

Enumerator

-0.15

veis

-0.14

éľ

-0.14

-Headers

-0.14

è¾°

-0.14

rou

-0.14

orrect

-0.13

ollider

-0.13

persona

-0.13

POSITIVE LOGITS

 Perc

0.15

 nackte

0.14

:::

0.14

 Pare

0.14

uve

0.14

 Kling

0.14

gew

0.14

 Rudd

0.13

 Middle

0.13

Activations Density 0.333%

words associated with social critique and moral accountability

No Comments

No Known Activations