INDEX

Explanations

causal relationships and connections between events

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

letic

-0.17

och

-0.16

éĸ

-0.15

ALI

-0.15

atures

-0.15

@dynamic

-0.15

áº¾

-0.14

alie

-0.14

Than

-0.14

andas

-0.14

POSITIVE LOGITS

ÏįÎ½

0.15

awl

0.15

_ATOMIC

0.14

anced

0.14

ARED

0.14

Ø¹Ø§ÙĨ

0.13

pei

0.13

OffsetTable

0.13

orf

0.13

Activations Density 0.179%

causal relationships and connections between events

No Comments

No Known Activations