INDEX

Explanations

words and phrases indicative of academic institutions and their designations

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

undi

-0.14

_footer

-0.14

 Discovery

-0.14

Ã¡m

-0.14

akis

-0.14

ãĥ¼ãĥł

-0.14

iegel

-0.14

io

-0.13

olume

-0.13

POSITIVE LOGITS

ALLY

0.16

 Sinclair

0.15

usters

0.15

entifier

0.14

ally

0.14

CFG

0.14

ycz

0.14

_QMARK

0.14

erÃ§

0.14

upo

0.14

Activations Density 0.007%

words and phrases indicative of academic institutions and their designations

No Comments

No Known Activations