INDEX

Explanations

references to app manifests

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

blick

-0.15

lect

-0.15

auga

-0.15

Bon

-0.15

loom

-0.14

 experienced

-0.13

ICC

-0.13

mo

-0.13

SizeMode

-0.13

 Furn

-0.13

POSITIVE LOGITS

eton

0.17

roman

0.15

ocide

0.14

Written

0.14

.TypeOf

0.14

alta

0.14

achuset

0.14

 extents

0.14

ossil

0.14

anela

0.14

Activations Density 0.004%

references to app manifests

No Comments

No Known Activations