INDEX

Explanations

repeated phrases indicating decision-making or choices

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aph

-0.17

 Mask

-0.16

oku

-0.15

ÑĭÐ²Ð°

-0.15

 scrub

-0.15

DOT

-0.14

Mask

-0.14

 Destiny

-0.14

subtype

-0.14

plat

-0.13

POSITIVE LOGITS

0.18

gregar

0.16

ëĭ´

0.16

pmat

0.16

umbs

0.15

å¤īãĤı

0.15

 Critical

0.14

 Thumb

0.14

orr

0.14

ê³

0.14

Activations Density 0.044%

repeated phrases indicating decision-making or choices

No Comments

No Known Activations