INDEX

Explanations

connections and comparisons between experiences, professions, and their long-term impacts or values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

afia

-0.16

aea

-0.15

izza

-0.15

 Sist

-0.14

æĩ

-0.14

 Profes

-0.14

eder

-0.14

anks

-0.13

ä»°

-0.13

ovol

-0.13

POSITIVE LOGITS

 generally

0.21

 otherwise

0.21

 overall

0.19

other

0.19

 other

0.18

 Ø§ÙĦØ£Ø®Ø±Ùī

0.18

otherwise

0.18

 general

0.17

.other

0.17

overall

0.16

Activations Density 0.289%

connections and comparisons between experiences, professions, and their long-term impacts or values

No Comments

No Known Activations