INDEX

Explanations

significant mentions of specific brands or products

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

thouse

-0.16

 passer

-0.15

thin

-0.14

Ø§Ø¯ÛĮ

-0.14

pass

-0.14

Ìģt

-0.14

ãĥĪãĥ«

-0.13

 Ø§ÙĦØ«

-0.13

_scheme

-0.13

erus

-0.13

POSITIVE LOGITS

arel

0.14

 ÐºÐ°Ñģ

0.14

ŀĭ

0.14

 Capability

0.13

ãĤ¼

0.13

 terror

0.13

 Trident

0.13

Cas

0.13

olle

0.13

 Fres

0.13

Activations Density 0.059%

significant mentions of specific brands or products

No Known Activations