INDEX

Explanations

negative sentiments or rejections of ideas

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

ymes

-0.17

EP

-0.15

 vÃ½

-0.15

Watcher

-0.14

orado

-0.14

 Ø¯ÙģØªØ±

-0.14

otta

-0.14

_CONTEXT

-0.14

isay

-0.14

ICES

-0.13

POSITIVE LOGITS

æķ´ä¸ª

0.25

 overall

0.23

 Ð²Ð¾Ð¾Ð±ÑīÐµ

0.23

overall

0.21

Overall

0.20

 altogether

0.20

 Overall

0.19

 entire

0.19

 Entire

0.17

ANDOM

0.16

Activations Density 0.219%

negative sentiments or rejections of ideas

No Comments

No Known Activations