INDEX

Explanations

terms and concepts related to locations and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

-0.15

stuff

-0.14

CodeGen

-0.14

ONTAL

-0.14

acre

-0.14

Stuff

-0.14

pawn

-0.14

ollo

-0.14

èĬ¬

-0.14

POSITIVE LOGITS

habi

0.17

ÐłÐĿ

0.16

Ã³mo

0.15

amam

0.14

.CustomButton

0.14

isman

0.14

eme

0.14

Moy

0.14

ewood

0.14

rete

0.14

Activations Density 0.256%

terms and concepts related to locations and their significance

No Comments

No Known Activations