INDEX

Explanations

occurrences of numbers and counting references

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

aupt

-0.18

rub

-0.17

tera

-0.16

uters

-0.15

ruba

-0.15

kel

-0.15

ronic

-0.15

Rub

-0.15

ãĥĩãĥ«

-0.14

unders

-0.14

POSITIVE LOGITS

pie

0.15

LOUR

0.14

azen

0.14

Registrar

0.14

Mt

0.14

 Pare

0.13

aday

0.13

 reconciliation

0.13

Ã¡lt

0.13

Activations Density 0.097%

occurrences of numbers and counting references

No Comments

No Known Activations