INDEX

Explanations

occurrences of the letter 'T' in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ensor

-0.19

reten

-0.18

uple

-0.18

ainer

-0.17

asks

-0.17

Ã¤ch

-0.17

ÙĦØ³

-0.17

ools

-0.16

aille

-0.16

opper

-0.16

POSITIVE LOGITS

otton

0.21

elf

0.17

ynes

0.17

iali

0.16

BC

0.15

ros

0.15

idy

0.15

annah

0.14

ople

0.14

yc

0.14

Activations Density 0.016%

occurrences of the letter 'T' in various contexts

No Comments

No Known Activations