INDEX

Explanations

phrases discussing changes and comparisons in conditions or characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

blr

-0.14

adÃŃ

-0.14

bridge

-0.13

sian

-0.13

wake

-0.13

éĭ

-0.13

cipher

-0.13

sdk

-0.13

ÑĦÐ¾ÑĢÑĤ

-0.13

baÅŁ

-0.13

POSITIVE LOGITS

 elsewhere

0.19

 otras

0.16

0.15

 bowl

0.15

ear

0.15

antium

0.14

 experienced

0.14

wiÄħ

0.14

 other

0.14

 Bowl

0.14

Activations Density 0.071%

phrases discussing changes and comparisons in conditions or characteristics

No Comments

No Known Activations