INDEX

Explanations

concepts related to secondary elements or issues in a narrative

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

Not in Any Lists

No Comments

Negative Logits

iete

-0.16

ucc

-0.16

ope

-0.15

rai

-0.15

ihar

-0.15

ervas

-0.15

ìĨ¡

-0.15

ophe

-0.14

Wire

-0.14

XL

-0.14

POSITIVE LOGITS

 secondary

0.16

enan

0.15

secondary

0.15

ãĥ¼ãĤ¯

0.15

ongo

0.15

oser

0.14

Secondary

0.14

 Secondary

0.14

mour

0.14

ziel

0.14

Activations Density 0.102%

concepts related to secondary elements or issues in a narrative

No Comments

No Known Activations