INDEX

Explanations

mentions of governmental or institutional actions and decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

mund

-0.15

inski

-0.15

agara

-0.14

rani

-0.14

mes

-0.14

iki

-0.13

odom

-0.13

ellen

-0.13

agina

-0.13

å¢ĥ

-0.13

POSITIVE LOGITS

 intim

0.22

 representations

0.21

 furn

0.18

int

0.18

 representation

0.17

 copy

0.17

 prima

0.17

ãĥ³ãĤ°ãĥ«

0.16

(Action

0.16

 chall

0.16

Activations Density 0.059%

mentions of governmental or institutional actions and decisions

No Comments

No Known Activations