INDEX

Explanations

phrases or terms related to geographical locations or sports contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

aeda

-0.18

hani

-0.15

 Cove

-0.15

ansa

-0.14

_MULT

-0.14

 Î´Î¹Î¬

-0.14

 Herr

-0.13

Inlining

-0.13

.Css

-0.13

 printk

-0.13

POSITIVE LOGITS

 SUBSTITUTE

0.17

aille

0.16

æī£

0.15

ailles

0.15

 whichever

0.14

 antid

0.14

åłĤ

0.14

 according

0.14

@g

0.14

ÑĨÑĥ

0.13

Activations Density 0.152%

phrases or terms related to geographical locations or sports contexts

No Comments

No Known Activations