INDEX

Explanations

actions related to accountability and the impact of decisions or behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

RC

-0.17

=Y

-0.14

ÑĢ

-0.14

rary

-0.14

 ÄĮeskÃ¡

-0.13

(åľŁ

-0.13

.setY

-0.13

ignite

-0.13

oure

-0.13

POSITIVE LOGITS

errat

0.16

 thereby

0.16

thumb

0.15

achten

0.15

lude

0.14

eman

0.14

VECTOR

0.14

sar

0.14

VOID

0.13

 hoped

0.13

Activations Density 0.116%

actions related to accountability and the impact of decisions or behaviors

No Comments

No Known Activations