INDEX

Explanations

specific terms related to geographical locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Alam

-0.15

 Nass

-0.15

 McGill

-0.14

ipmap

-0.14

egot

-0.13

rych

-0.13

ÏĨÏħ

-0.13

baugh

-0.13

ÑģÐ¸Ð¹

-0.13

iscard

-0.13

POSITIVE LOGITS

Hen

0.78

Jen

0.76

hen

0.74

Hen

0.72

len

0.71

hen

0.69

len

0.68

Ken

0.68

HEN

0.66

Len

0.66

Activations Density 0.781%

specific terms related to geographical locations and entities

No Comments

No Known Activations