INDEX

Explanations

the suffix "ent" indicating action or state

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

 Clown

-0.16

ÙĬØ«

-0.15

 Boone

-0.15

egers

-0.15

è¿«

-0.15

iegel

-0.15

 meaning

-0.14

 Meaning

-0.14

.nextElement

-0.14

POSITIVE LOGITS

nock

0.16

ivec

0.16

WithDuration

0.15

.LENGTH

0.15

ÏĦÎ¿Î»

0.15

Ø¯ÙĪØ§Ø¬

0.14

obar

0.14

swer

0.14

oller

0.14

 knull

0.14

Activations Density 0.000%

the suffix "ent" indicating action or state

No Comments

No Known Activations