INDEX

Explanations

the presence of Spanish verbs, particularly forms of "ser" and "ir"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

cher

-0.17

-0.16

avail

-0.15

ariat

-0.15

tte

-0.14

regar

-0.14

geois

-0.14

.ua

-0.14

POSITIVE LOGITS

Kul

0.14

Å¯l

0.14

scoped

0.14

stdin

0.13

eyh

0.13

eyse

0.13

adÄ±r

0.12

URA

0.12

abin

0.12

oma

0.12

Activations Density 0.044%

the presence of Spanish verbs, particularly forms of "ser" and "ir"

No Comments

No Known Activations